Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 122 results for author: <span class="mathjax">Gomez, A</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Gomez%2C+A">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Gomez, A"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Gomez%2C+A&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Gomez, A"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.06108">arXiv:2501.06108</a> <span> [<a href="https://arxiv.org/pdf/2501.06108">pdf</a>, <a href="https://arxiv.org/format/2501.06108">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Disordered Systems and Neural Networks">cond-mat.dis-nn</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistical Mechanics">cond-mat.stat-mech</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Inferring High-Order Couplings with Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Decelle%2C+A">Aur茅lien Decelle</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A+d+J+N">Alfonso de Jes煤s Navas G贸mez</a>, <a href="/search/cs?searchtype=author&query=Seoane%2C+B">Beatriz Seoane</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.06108v2-abstract-short" style="display: inline;"> Maximum entropy methods, based on the inverse Ising/Potts problem from statistical mechanics, are essential for modeling interactions between pairs of variables in data-driven problems across disciplines such as bioinformatics, ecology, and neuroscience. Despite their considerable success, these methods typically fail to capture higher-order interactions that are often essential for understanding… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06108v2-abstract-full').style.display = 'inline'; document.getElementById('2501.06108v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.06108v2-abstract-full" style="display: none;"> Maximum entropy methods, based on the inverse Ising/Potts problem from statistical mechanics, are essential for modeling interactions between pairs of variables in data-driven problems across disciplines such as bioinformatics, ecology, and neuroscience. Despite their considerable success, these methods typically fail to capture higher-order interactions that are often essential for understanding complex systems. Conversely, modern machine learning methods capture these complex interactions, but the computational cost of interpretable frameworks makes them impractical for real-world applications. Restricted Boltzmann Machines (RBMs) provide a computationally efficient way to capture statistical correlations using hidden nodes in a bipartite neural network. In this study, we introduce a new method that maps RBMs to generalized Potts models, allowing for the extraction of interactions up to any specified order. This method utilizes large-$N$ approximations, enabled by the RBM's simple structure, to extract effective many-body couplings with minimal computational effort. Furthermore, we propose a robust framework for extracting higher-order interactions in more complex probabilistic models and a simple gauge-fixing method within the effective many-body Potts model. Our validation on synthetic datasets confirms the method's ability to recover two- and three-body interactions accurately. When applied to protein sequence data, the framework competently reconstructs protein contact maps and provides performance comparable to the best inverse Potts models. These findings confirm that RBMs are an effective and streamlined tool for exploring higher-order interactions within complex systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06108v2-abstract-full').style.display = 'none'; document.getElementById('2501.06108v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 Pages and 5 Figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.17116">arXiv:2412.17116</a> <span> [<a href="https://arxiv.org/pdf/2412.17116">pdf</a>, <a href="https://arxiv.org/format/2412.17116">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Fair and Accurate Regression: Strong Formulations and Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deza%2C+A">Anna Deza</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a>, <a href="/search/cs?searchtype=author&query=Atamt%C3%BCrk%2C+A">Alper Atamt眉rk</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.17116v1-abstract-short" style="display: inline;"> This paper introduces mixed-integer optimization methods to solve regression problems that incorporate fairness metrics. We propose an exact formulation for training fair regression models. To tackle this computationally hard problem, we study the polynomially-solvable single-factor and single-observation subproblems as building blocks and derive their closed convex hull descriptions. Strong formu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17116v1-abstract-full').style.display = 'inline'; document.getElementById('2412.17116v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.17116v1-abstract-full" style="display: none;"> This paper introduces mixed-integer optimization methods to solve regression problems that incorporate fairness metrics. We propose an exact formulation for training fair regression models. To tackle this computationally hard problem, we study the polynomially-solvable single-factor and single-observation subproblems as building blocks and derive their closed convex hull descriptions. Strong formulations obtained for the general fair regression problem in this manner are utilized to solve the problem with a branch-and-bound algorithm exactly or as a relaxation to produce fair and accurate models rapidly. Moreover, to handle large-scale instances, we develop a coordinate descent algorithm motivated by the convex-hull representation of the single-factor fair regression problem to improve a given solution efficiently. Numerical experiments conducted on fair least squares and fair logistic regression problems show competitive statistical performance with state-of-the-art methods while significantly reducing training times. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.17116v1-abstract-full').style.display = 'none'; document.getElementById('2412.17116v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.04261">arXiv:2412.04261</a> <span> [<a href="https://arxiv.org/pdf/2412.04261">pdf</a>, <a href="https://arxiv.org/format/2412.04261">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dang%2C+J">John Dang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+S">Shivalika Singh</a>, <a href="/search/cs?searchtype=author&query=D%27souza%2C+D">Daniel D'souza</a>, <a href="/search/cs?searchtype=author&query=Ahmadian%2C+A">Arash Ahmadian</a>, <a href="/search/cs?searchtype=author&query=Salamanca%2C+A">Alejandro Salamanca</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+M">Madeline Smith</a>, <a href="/search/cs?searchtype=author&query=Peppin%2C+A">Aidan Peppin</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+S">Sungjin Hong</a>, <a href="/search/cs?searchtype=author&query=Govindassamy%2C+M">Manoj Govindassamy</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+T">Terrence Zhao</a>, <a href="/search/cs?searchtype=author&query=Kublik%2C+S">Sandra Kublik</a>, <a href="/search/cs?searchtype=author&query=Amer%2C+M">Meor Amer</a>, <a href="/search/cs?searchtype=author&query=Aryabumi%2C+V">Viraat Aryabumi</a>, <a href="/search/cs?searchtype=author&query=Campos%2C+J+A">Jon Ander Campos</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Y">Yi-Chern Tan</a>, <a href="/search/cs?searchtype=author&query=Kocmi%2C+T">Tom Kocmi</a>, <a href="/search/cs?searchtype=author&query=Strub%2C+F">Florian Strub</a>, <a href="/search/cs?searchtype=author&query=Grinsztajn%2C+N">Nathan Grinsztajn</a>, <a href="/search/cs?searchtype=author&query=Flet-Berliac%2C+Y">Yannis Flet-Berliac</a>, <a href="/search/cs?searchtype=author&query=Locatelli%2C+A">Acyr Locatelli</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hangyu Lin</a>, <a href="/search/cs?searchtype=author&query=Talupuru%2C+D">Dwarak Talupuru</a>, <a href="/search/cs?searchtype=author&query=Venkitesh%2C+B">Bharat Venkitesh</a>, <a href="/search/cs?searchtype=author&query=Cairuz%2C+D">David Cairuz</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+B">Bowen Yang</a> , et al. (20 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.04261v1-abstract-short" style="display: inline;"> We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly performant multilingual models that match or surpass the capabilities of monolingual models. By leveraging several years of research at Cohere For AI and Cohere, including advancements in data arbitrage, multilingual prefere… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04261v1-abstract-full').style.display = 'inline'; document.getElementById('2412.04261v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.04261v1-abstract-full" style="display: none;"> We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly performant multilingual models that match or surpass the capabilities of monolingual models. By leveraging several years of research at Cohere For AI and Cohere, including advancements in data arbitrage, multilingual preference training, and model merging, Aya Expanse sets a new state-of-the-art in multilingual performance. Our evaluations on the Arena-Hard-Auto dataset, translated into 23 languages, demonstrate that Aya Expanse 8B and 32B outperform leading open-weight models in their respective parameter classes, including Gemma 2, Qwen 2.5, and Llama 3.1, achieving up to a 76.6% win-rate. Notably, Aya Expanse 32B outperforms Llama 3.1 70B, a model with twice as many parameters, achieving a 54.0% win-rate. In this short technical report, we present extended evaluation results for the Aya Expanse model family and release their open-weights, together with a new multilingual evaluation dataset m-ArenaHard. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.04261v1-abstract-full').style.display = 'none'; document.getElementById('2412.04261v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11190">arXiv:2411.11190</a> <span> [<a href="https://arxiv.org/pdf/2411.11190">pdf</a>, <a href="https://arxiv.org/format/2411.11190">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> DeepSPV: An Interpretable Deep Learning Pipeline for 3D Spleen Volume Estimation from 2D Ultrasound Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+Z">Zhen Yuan</a>, <a href="/search/cs?searchtype=author&query=Stojanovski%2C+D">David Stojanovski</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lei Li</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Jogeesvaran%2C+H">Haran Jogeesvaran</a>, <a href="/search/cs?searchtype=author&query=Puyol-Ant%C3%B3n%2C+E">Esther Puyol-Ant贸n</a>, <a href="/search/cs?searchtype=author&query=Inusa%2C+B">Baba Inusa</a>, <a href="/search/cs?searchtype=author&query=King%2C+A+P">Andrew P. King</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11190v1-abstract-short" style="display: inline;"> Splenomegaly, the enlargement of the spleen, is an important clinical indicator for various associated medical conditions, such as sickle cell disease (SCD). Spleen length measured from 2D ultrasound is the most widely used metric for characterising spleen size. However, it is still considered a surrogate measure, and spleen volume remains the gold standard for assessing spleen size. Accurate sple… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11190v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11190v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11190v1-abstract-full" style="display: none;"> Splenomegaly, the enlargement of the spleen, is an important clinical indicator for various associated medical conditions, such as sickle cell disease (SCD). Spleen length measured from 2D ultrasound is the most widely used metric for characterising spleen size. However, it is still considered a surrogate measure, and spleen volume remains the gold standard for assessing spleen size. Accurate spleen volume measurement typically requires 3D imaging modalities, such as computed tomography or magnetic resonance imaging, but these are not widely available, especially in the Global South which has a high prevalence of SCD. In this work, we introduce a deep learning pipeline, DeepSPV, for precise spleen volume estimation from single or dual 2D ultrasound images. The pipeline involves a segmentation network and a variational autoencoder for learning low-dimensional representations from the estimated segmentations. We investigate three approaches for spleen volume estimation and our best model achieves 86.62%/92.5% mean relative volume accuracy (MRVA) under single-view/dual-view settings, surpassing the performance of human experts. In addition, the pipeline can provide confidence intervals for the volume estimates as well as offering benefits in terms of interpretability, which further support clinicians in decision-making when identifying splenomegaly. We evaluate the full pipeline using a highly realistic synthetic dataset generated by a diffusion model, achieving an overall MRVA of 83.0% from a single 2D ultrasound image. Our proposed DeepSPV is the first work to use deep learning to estimate 3D spleen volume from 2D ultrasound images and can be seamlessly integrated into the current clinical workflow for spleen assessment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11190v1-abstract-full').style.display = 'none'; document.getElementById('2411.11190v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2308.08038</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19371">arXiv:2409.19371</a> <span> [<a href="https://arxiv.org/pdf/2409.19371">pdf</a>, <a href="https://arxiv.org/format/2409.19371">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stojanovski%2C+D">David Stojanovski</a>, <a href="/search/cs?searchtype=author&query=da+Silva%2C+M">Mariana da Silva</a>, <a href="/search/cs?searchtype=author&query=Lamata%2C+P">Pablo Lamata</a>, <a href="/search/cs?searchtype=author&query=Beqiri%2C+A">Arian Beqiri</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.19371v1-abstract-short" style="display: inline;"> We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $螕$-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19371v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19371v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19371v1-abstract-full" style="display: none;"> We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $螕$-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks. We compared six diffusion models in terms of the computational cost of generating synthetic 2D echo data, the visual realism of the resulting images, and the performance, on real data, of downstream tasks (segmentation and classification) trained using these synthetic echoes. We compare various diffusion strategies and ODE solvers for their impact on segmentation and classification performance. The results show that our propose architectures significantly reduce computational costs while maintaining or improving downstream task performance compared to state-of-the-art methods. While other diffusion models generated more realistic-looking echo images at higher computational cost, our research suggests that for model training, visual realism is not necessarily related to model performance, and considerable compute costs can be saved by using more efficient models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19371v1-abstract-full').style.display = 'none'; document.getElementById('2409.19371v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17214">arXiv:2409.17214</a> <span> [<a href="https://arxiv.org/pdf/2409.17214">pdf</a>, <a href="https://arxiv.org/format/2409.17214">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Grounded Predictions of Teamwork as a One-Shot Game: A Multiagent Multi-Armed Bandits Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A+L+d+A">Alejandra L贸pez de Aberasturi G贸mez</a>, <a href="/search/cs?searchtype=author&query=Sierra%2C+C">Carles Sierra</a>, <a href="/search/cs?searchtype=author&query=Sabater-Mir%2C+J">Jordi Sabater-Mir</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17214v1-abstract-short" style="display: inline;"> Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, self-interested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17214v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17214v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17214v1-abstract-full" style="display: none;"> Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, self-interested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner's theory of group productivity. We characterise this novel game's Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty influence agents' strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating findings from social psychology research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17214v1-abstract-full').style.display = 'none'; document.getElementById('2409.17214v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09645">arXiv:2409.09645</a> <span> [<a href="https://arxiv.org/pdf/2409.09645">pdf</a>, <a href="https://arxiv.org/format/2409.09645">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3627673.3679891">10.1145/3627673.3679891 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Barreda%2C+J">Jesus Barreda</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Ashley Gomez</a>, <a href="/search/cs?searchtype=author&query=Puga%2C+R">Ruben Puga</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+K">Kaixiong Zhou</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Li Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.09645v1-abstract-short" style="display: inline;"> Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. only a limited number of samples per class are available… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09645v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09645v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09645v1-abstract-full" style="display: none;"> Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. only a limited number of samples per class are available in training data, DNNs show a significant drop in testing accuracy and poor generalization ability. In this paper, we propose to address these problems from an optimization and a loss function perspective. Specifically, we propose a new learning framework named COSCO consisting of a sharpness-aware minimization (SAM) optimization and a Prototypical loss function to improve the generalization ability of DNN for multivariate time series classification problems under few-shot setting. Our experiments demonstrate our proposed method outperforms the existing baseline methods. Our source code is available at: https://github.com/JRB9/COSCO. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09645v1-abstract-full').style.display = 'none'; document.getElementById('2409.09645v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figures, CIKM '24 Short Paper Track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.10361">arXiv:2408.10361</a> <span> [<a href="https://arxiv.org/pdf/2408.10361">pdf</a>, <a href="https://arxiv.org/format/2408.10361">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> ASASVIcomtech: The Vicomtech-UGR Speech Deepfake Detection and SASV Systems for the ASVspoof5 Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mart%C3%ADn-Do%C3%B1as%2C+J+M">Juan M. Mart铆n-Do帽as</a>, <a href="/search/cs?searchtype=author&query=Rosell%C3%B3%2C+E">Eros Rosell贸</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A+M">Angel M. Gomez</a>, <a href="/search/cs?searchtype=author&query=%C3%81lvarez%2C+A">Aitor 脕lvarez</a>, <a href="/search/cs?searchtype=author&query=L%C3%B3pez-Espejo%2C+I">Iv谩n L贸pez-Espejo</a>, <a href="/search/cs?searchtype=author&query=Peinado%2C+A+M">Antonio M. Peinado</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.10361v1-abstract-short" style="display: inline;"> This paper presents the work carried out by the ASASVIcomtech team, made up of researchers from Vicomtech and University of Granada, for the ASVspoof5 Challenge. The team has participated in both Track 1 (speech deepfake detection) and Track 2 (spoofing-aware speaker verification). This work started with an analysis of the challenge available data, which was regarded as an essential step to avoid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10361v1-abstract-full').style.display = 'inline'; document.getElementById('2408.10361v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.10361v1-abstract-full" style="display: none;"> This paper presents the work carried out by the ASASVIcomtech team, made up of researchers from Vicomtech and University of Granada, for the ASVspoof5 Challenge. The team has participated in both Track 1 (speech deepfake detection) and Track 2 (spoofing-aware speaker verification). This work started with an analysis of the challenge available data, which was regarded as an essential step to avoid later potential biases of the trained models, and whose main conclusions are presented here. With respect to the proposed approaches, a closed-condition system employing a deep complex convolutional recurrent architecture was developed for Track 1, although, unfortunately, no noteworthy results were achieved. On the other hand, different possibilities of open-condition systems, based on leveraging self-supervised models, augmented training data from previous challenges, and novel vocoders, were explored for both tracks, finally achieving very competitive results with an ensemble system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10361v1-abstract-full').style.display = 'none'; document.getElementById('2408.10361v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper was accepted at ASVspoof Workshop 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.21577">arXiv:2407.21577</a> <span> [<a href="https://arxiv.org/pdf/2407.21577">pdf</a>, <a href="https://arxiv.org/format/2407.21577">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Multi-Site Class-Incremental Learning with Weighted Experts in Echocardiography </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bransby%2C+K+M">Kit M. Bransby</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+W+C">Woo-jin Cho Kim</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+J">Jorge Oliveira</a>, <a href="/search/cs?searchtype=author&query=Thorley%2C+A">Alex Thorley</a>, <a href="/search/cs?searchtype=author&query=Beqiri%2C+A">Arian Beqiri</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Chartsias%2C+A">Agisilaos Chartsias</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.21577v1-abstract-short" style="display: inline;"> Building an echocardiography view classifier that maintains performance in real-life cases requires diverse multi-site data, and frequent updates with newly available data to mitigate model drift. Simply fine-tuning on new datasets results in "catastrophic forgetting", and cannot adapt to variations of view labels between sites. Alternatively, collecting all data on a single server and re-training… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21577v1-abstract-full').style.display = 'inline'; document.getElementById('2407.21577v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.21577v1-abstract-full" style="display: none;"> Building an echocardiography view classifier that maintains performance in real-life cases requires diverse multi-site data, and frequent updates with newly available data to mitigate model drift. Simply fine-tuning on new datasets results in "catastrophic forgetting", and cannot adapt to variations of view labels between sites. Alternatively, collecting all data on a single server and re-training may not be feasible as data sharing agreements may restrict image transfer, or datasets may only become available at different times. Furthermore, time and cost associated with re-training grows with every new dataset. We propose a class-incremental learning method which learns an expert network for each dataset, and combines all expert networks with a score fusion model. The influence of ``unqualified experts'' is minimised by weighting each contribution with a learnt in-distribution score. These weights promote transparency as the contribution of each expert is known during inference. Instead of using the original images, we use learned features from each dataset, which are easier to share and raise fewer licensing and privacy concerns. We validate our work on six datasets from multiple sites, demonstrating significant reductions in training time while improving view classification performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21577v1-abstract-full').style.display = 'none'; document.getElementById('2407.21577v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for Oral at MICCAI workshop ASMUS-2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.19637">arXiv:2407.19637</a> <span> [<a href="https://arxiv.org/pdf/2407.19637">pdf</a>, <a href="https://arxiv.org/format/2407.19637">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TPDS.2024.3430853">10.1109/TPDS.2024.3430853 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> STT-RAM-based Hierarchical In-Memory Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gajaria%2C+D">Dhruv Gajaria</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+K+A">Kevin Antony Gomez</a>, <a href="/search/cs?searchtype=author&query=Adegbija%2C+T">Tosiron Adegbija</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.19637v1-abstract-short" style="display: inline;"> In-memory computing promises to overcome the von Neumann bottleneck in computer systems by performing computations directly within the memory. Previous research has suggested using Spin-Transfer Torque RAM (STT-RAM) for in-memory computing due to its non-volatility, low leakage power, high density, endurance, and commercial viability. This paper explores hierarchical in-memory computing, where dif… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.19637v1-abstract-full').style.display = 'inline'; document.getElementById('2407.19637v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.19637v1-abstract-full" style="display: none;"> In-memory computing promises to overcome the von Neumann bottleneck in computer systems by performing computations directly within the memory. Previous research has suggested using Spin-Transfer Torque RAM (STT-RAM) for in-memory computing due to its non-volatility, low leakage power, high density, endurance, and commercial viability. This paper explores hierarchical in-memory computing, where different levels of the memory hierarchy are augmented with processing elements to optimize workload execution. The paper investigates processing in memory (PiM) using non-volatile STT-RAM and processing in cache (PiC) using volatile STT-RAM with relaxed retention, which helps mitigate STT-RAM's write latency and energy overheads. We analyze tradeoffs and overheads associated with data movement for PiC versus write overheads for PiM using STT-RAMs for various workloads. We examine workload characteristics, such as computational intensity and CPU-dependent workloads with limited instruction-level parallelism, and their impact on PiC/PiM tradeoffs. Using these workloads, we evaluate computing in STT-RAM versus SRAM at different cache hierarchy levels and explore the potential of heterogeneous STT-RAM cache architectures with various retention times for PiC and CPU-based computing. Our experiments reveal significant advantages of STT-RAM-based PiC over PiM for specific workloads. Finally, we describe open research problems in hierarchical in-memory computing architectures to further enhance this paradigm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.19637v1-abstract-full').style.display = 'none'; document.getElementById('2407.19637v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in: IEEE Transactions on Parallel and Distributed Systems ( Volume: 35, Issue: 9, September 2024)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Parallel and Distributed Systems, vol. 35, no. 9, pp. 1615-1629, Sept. 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19148">arXiv:2406.19148</a> <span> [<a href="https://arxiv.org/pdf/2406.19148">pdf</a>, <a href="https://arxiv.org/format/2406.19148">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bransby%2C+K+M">Kit Mills Bransby</a>, <a href="/search/cs?searchtype=author&query=Beqiri%2C+A">Arian Beqiri</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+W+C">Woo-Jin Cho Kim</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+J">Jorge Oliveira</a>, <a href="/search/cs?searchtype=author&query=Chartsias%2C+A">Agisilaos Chartsias</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.19148v1-abstract-short" style="display: inline;"> Neural networks can learn spurious correlations that lead to the correct prediction in a validation set, but generalise poorly because the predictions are right for the wrong reason. This undesired learning of naive shortcuts (Clever Hans effect) can happen for example in echocardiogram view classification when background cues (e.g. metadata) are biased towards a class and the model learns to focu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19148v1-abstract-full').style.display = 'inline'; document.getElementById('2406.19148v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19148v1-abstract-full" style="display: none;"> Neural networks can learn spurious correlations that lead to the correct prediction in a validation set, but generalise poorly because the predictions are right for the wrong reason. This undesired learning of naive shortcuts (Clever Hans effect) can happen for example in echocardiogram view classification when background cues (e.g. metadata) are biased towards a class and the model learns to focus on those background features instead of on the image content. We propose a simple, yet effective random background augmentation method called BackMix, which samples random backgrounds from other examples in the training set. By enforcing the background to be uncorrelated with the outcome, the model learns to focus on the data within the ultrasound sector and becomes invariant to the regions outside this. We extend our method in a semi-supervised setting, finding that the positive effects of BackMix are maintained with as few as 5% of segmentation labels. A loss weighting mechanism, wBackMix, is also proposed to increase the contribution of the augmented examples. We validate our method on both in-distribution and out-of-distribution datasets, demonstrating significant improvements in classification accuracy, region focus and generalisability. Our source code is available at: https://github.com/kitbransby/BackMix <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19148v1-abstract-full').style.display = 'none'; document.getElementById('2406.19148v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at MICCAI 2024 (Pre-print)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.17303">arXiv:2406.17303</a> <span> [<a href="https://arxiv.org/pdf/2406.17303">pdf</a>, <a href="https://arxiv.org/format/2406.17303">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Learnings from Implementation of a BDI Agent-based Battery-less Wireless Sensor </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ramanathan%2C+G">Ganesh Ramanathan</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Andres Gomez</a>, <a href="/search/cs?searchtype=author&query=Mayer%2C+S">Simon Mayer</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.17303v1-abstract-short" style="display: inline;"> Battery-less embedded devices powered by energy harvesting are increasingly being used in wireless sensing applications. However, their limited and often uncertain energy availability challenges designing application programs. To examine if BDI-based agent programming can address this challenge, we used it for a real-life application involving an environmental sensor that works on energy harvested… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17303v1-abstract-full').style.display = 'inline'; document.getElementById('2406.17303v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.17303v1-abstract-full" style="display: none;"> Battery-less embedded devices powered by energy harvesting are increasingly being used in wireless sensing applications. However, their limited and often uncertain energy availability challenges designing application programs. To examine if BDI-based agent programming can address this challenge, we used it for a real-life application involving an environmental sensor that works on energy harvested from ambient light. This yielded the first ever implementation of a BDI agent on a low-power battery-less and energy-harvesting embedded system. Furthermore, it uncovered conceptual integration challenges between embedded systems and BDI-based agent programming that, if overcome, will simplify the deployment of more autonomous systems on low-power devices with non-deterministic energy availability. Specifically, we (1) mapped essential device states to default \textit{internal} beliefs, (2) recognized and addressed the need for beliefs in general to be \textit{short-} or \textit{long-term}, and (3) propose dynamic annotation of intentions with their run-time energy impact. We show that incorporating these extensions not only simplified the programming but also improved code readability and understanding of its behavior. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17303v1-abstract-full').style.display = 'none'; document.getElementById('2406.17303v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.00808">arXiv:2406.00808</a> <span> [<a href="https://arxiv.org/pdf/2406.00808">pdf</a>, <a href="https://arxiv.org/format/2406.00808">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reynaud%2C+H">Hadrien Reynaud</a>, <a href="/search/cs?searchtype=author&query=Meng%2C+Q">Qingjie Meng</a>, <a href="/search/cs?searchtype=author&query=Dombrowski%2C+M">Mischa Dombrowski</a>, <a href="/search/cs?searchtype=author&query=Ghosh%2C+A">Arijit Ghosh</a>, <a href="/search/cs?searchtype=author&query=Day%2C+T">Thomas Day</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Leeson%2C+P">Paul Leeson</a>, <a href="/search/cs?searchtype=author&query=Kainz%2C+B">Bernhard Kainz</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.00808v1-abstract-short" style="display: inline;"> To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data. Until now, generative methods have faced constraints in terms of fidelity, spatio-temporal coherence, and the length of generation, failing to capture the complete details of dataset distributions. We present a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00808v1-abstract-full').style.display = 'inline'; document.getElementById('2406.00808v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00808v1-abstract-full" style="display: none;"> To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data. Until now, generative methods have faced constraints in terms of fidelity, spatio-temporal coherence, and the length of generation, failing to capture the complete details of dataset distributions. We present a model designed to produce high-fidelity, long and complete data samples with near-real-time efficiency and explore our approach on a challenging task: generating echocardiogram videos. We develop our generation method based on diffusion models and introduce a protocol for medical video dataset anonymization. As an exemplar, we present EchoNet-Synthetic, a fully synthetic, privacy-compliant echocardiogram dataset with paired ejection fraction labels. As part of our de-identification protocol, we evaluate the quality of the generated dataset and propose to use clinical downstream tasks as a measurement on top of widely used but potentially biased image quality metrics. Experimental outcomes demonstrate that EchoNet-Synthetic achieves comparable dataset fidelity to the actual dataset, effectively supporting the ejection fraction regression task. Code, weights and dataset are available at https://github.com/HReynaud/EchoNet-Synthetic. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00808v1-abstract-full').style.display = 'none'; document.getElementById('2406.00808v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at MICCAI 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.15032">arXiv:2405.15032</a> <span> [<a href="https://arxiv.org/pdf/2405.15032">pdf</a>, <a href="https://arxiv.org/format/2405.15032">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Aya 23: Open Weight Releases to Further Multilingual Progress </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aryabumi%2C+V">Viraat Aryabumi</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+J">John Dang</a>, <a href="/search/cs?searchtype=author&query=Talupuru%2C+D">Dwarak Talupuru</a>, <a href="/search/cs?searchtype=author&query=Dash%2C+S">Saurabh Dash</a>, <a href="/search/cs?searchtype=author&query=Cairuz%2C+D">David Cairuz</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+H">Hangyu Lin</a>, <a href="/search/cs?searchtype=author&query=Venkitesh%2C+B">Bharat Venkitesh</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+M">Madeline Smith</a>, <a href="/search/cs?searchtype=author&query=Campos%2C+J+A">Jon Ander Campos</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+Y+C">Yi Chern Tan</a>, <a href="/search/cs?searchtype=author&query=Marchisio%2C+K">Kelly Marchisio</a>, <a href="/search/cs?searchtype=author&query=Bartolo%2C+M">Max Bartolo</a>, <a href="/search/cs?searchtype=author&query=Ruder%2C+S">Sebastian Ruder</a>, <a href="/search/cs?searchtype=author&query=Locatelli%2C+A">Acyr Locatelli</a>, <a href="/search/cs?searchtype=author&query=Kreutzer%2C+J">Julia Kreutzer</a>, <a href="/search/cs?searchtype=author&query=Frosst%2C+N">Nick Frosst</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Aidan Gomez</a>, <a href="/search/cs?searchtype=author&query=Blunsom%2C+P">Phil Blunsom</a>, <a href="/search/cs?searchtype=author&query=Fadaee%2C+M">Marzieh Fadaee</a>, <a href="/search/cs?searchtype=author&query=%C3%9Cst%C3%BCn%2C+A">Ahmet 脺st眉n</a>, <a href="/search/cs?searchtype=author&query=Hooker%2C+S">Sara Hooker</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.15032v2-abstract-short" style="display: inline;"> This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model (脺st眉n et al., 2024), focusing on pairing a highly performant pre-trained model with the recently released Aya collection (Singh et al., 2024). The result is a powerful multilingual large language model serving 23 languages, expanding state-of-art language modelin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15032v2-abstract-full').style.display = 'inline'; document.getElementById('2405.15032v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15032v2-abstract-full" style="display: none;"> This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model (脺st眉n et al., 2024), focusing on pairing a highly performant pre-trained model with the recently released Aya collection (Singh et al., 2024). The result is a powerful multilingual large language model serving 23 languages, expanding state-of-art language modeling capabilities to approximately half of the world's population. The Aya model covered 101 languages whereas Aya 23 is an experiment in depth vs breadth, exploring the impact of allocating more capacity to fewer languages that are included during pre-training. Aya 23 outperforms both previous massively multilingual models like Aya 101 for the languages it covers, as well as widely used models like Gemma, Mistral and Mixtral on an extensive range of discriminative and generative tasks. We release the open weights for both the 8B and 35B models as part of our continued commitment for expanding access to multilingual progress. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15032v2-abstract-full').style.display = 'none'; document.getElementById('2405.15032v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.15320">arXiv:2404.15320</a> <span> [<a href="https://arxiv.org/pdf/2404.15320">pdf</a>, <a href="https://arxiv.org/format/2404.15320">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Using Large Language Models to Enrich the Documentation of Datasets for Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Giner-Miguelez%2C+J">Joan Giner-Miguelez</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Abel G贸mez</a>, <a href="/search/cs?searchtype=author&query=Cabot%2C+J">Jordi Cabot</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.15320v2-abstract-short" style="display: inline;"> Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and social concerns. However, this information is typically presented as unstructured text in accompanying documentation, hampering their automated analysis and proces… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15320v2-abstract-full').style.display = 'inline'; document.getElementById('2404.15320v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.15320v2-abstract-full" style="display: none;"> Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and social concerns. However, this information is typically presented as unstructured text in accompanying documentation, hampering their automated analysis and processing. In this work, we explore using large language models (LLM) and a set of prompting strategies to automatically extract these dimensions from documents and enrich the dataset description with them. Our approach could aid data publishers and practitioners in creating machine-readable documentation to improve the discoverability of their datasets, assess their compliance with current AI regulations, and improve the overall quality of ML models trained on them. In this paper, we evaluate the approach on 12 scientific dataset papers published in two scientific journals (Nature's Scientific Data and Elsevier's Data in Brief) using two different LLMs (GPT3.5 and Flan-UL2). Results show good accuracy with our prompt extraction strategies. Concrete results vary depending on the dimensions, but overall, GPT3.5 shows slightly better accuracy (81,21%) than FLAN-UL2 (69,13%) although it is more prone to hallucinations. We have released an open-source tool implementing our approach and a replication package, including the experiments' code and results, in an open-source repository. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15320v2-abstract-full').style.display = 'none'; document.getElementById('2404.15320v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.4.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.14848">arXiv:2404.14848</a> <span> [<a href="https://arxiv.org/pdf/2404.14848">pdf</a>, <a href="https://arxiv.org/format/2404.14848">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Evaluating Dynamic Environment Difficulty for Obstacle Avoidance Benchmarking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+M">Moji Shi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+G">Gang Chen</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+%C3%81+S">脕lvaro Serra G贸mez</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+S">Siyuan Wu</a>, <a href="/search/cs?searchtype=author&query=Alonso-Mora%2C+J">Javier Alonso-Mora</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.14848v1-abstract-short" style="display: inline;"> Dynamic obstacle avoidance is a popular research topic for autonomous systems, such as micro aerial vehicles and service robots. Accurately evaluating the performance of dynamic obstacle avoidance methods necessitates the establishment of a metric to quantify the environment's difficulty, a crucial aspect that remains unexplored. In this paper, we propose four metrics to measure the difficulty of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14848v1-abstract-full').style.display = 'inline'; document.getElementById('2404.14848v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14848v1-abstract-full" style="display: none;"> Dynamic obstacle avoidance is a popular research topic for autonomous systems, such as micro aerial vehicles and service robots. Accurately evaluating the performance of dynamic obstacle avoidance methods necessitates the establishment of a metric to quantify the environment's difficulty, a crucial aspect that remains unexplored. In this paper, we propose four metrics to measure the difficulty of dynamic environments. These metrics aim to comprehensively capture the influence of obstacles' number, size, velocity, and other factors on the difficulty. We compare the proposed metrics with existing static environment difficulty metrics and validate them through over 1.5 million trials in a customized simulator. This simulator excludes the effects of perception and control errors and supports different motion and gaze planners for obstacle avoidance. The results indicate that the survivability metric outperforms and establishes a monotonic relationship between the success rate, with a Spearman's Rank Correlation Coefficient (SRCC) of over 0.9. Specifically, for every planner, lower survivability leads to a higher success rate. This metric not only facilitates fair and comprehensive benchmarking but also provides insights for refining collision avoidance methods, thereby furthering the evolution of autonomous systems in dynamic environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14848v1-abstract-full').style.display = 'none'; document.getElementById('2404.14848v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.02251">arXiv:2404.02251</a> <span> [<a href="https://arxiv.org/pdf/2404.02251">pdf</a>, <a href="https://arxiv.org/format/2404.02251">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Generating gaussian pseudorandom noise with binary sequences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Soto%2C+F">Francisco-Javier Soto</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A+I">Ana I. G贸mez</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez-P%C3%A9rez%2C+D">Domingo G贸mez-P茅rez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.02251v1-abstract-short" style="display: inline;"> Gaussian random number generators attract a widespread interest due to their applications in several fields. Important requirements include easy implementation, tail accuracy, and, finally, a flat spectrum. In this work, we study the applicability of uniform pseudorandom binary generators in combination with the Central Limit Theorem to propose an easy to implement, efficient and flexible algorith… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02251v1-abstract-full').style.display = 'inline'; document.getElementById('2404.02251v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.02251v1-abstract-full" style="display: none;"> Gaussian random number generators attract a widespread interest due to their applications in several fields. Important requirements include easy implementation, tail accuracy, and, finally, a flat spectrum. In this work, we study the applicability of uniform pseudorandom binary generators in combination with the Central Limit Theorem to propose an easy to implement, efficient and flexible algorithm that leverages the properties of the pseudorandom binary generator used as an input, specially with respect to the correlation measure of higher order, to guarantee the quality of the generated samples. Our main result provides a relationship between the pseudorandomness of the input and the statistical moments of the output. We propose a design based on the combination of pseudonoise sequences commonly used on wireless communications with known hardware implementation, which can generate sequences with guaranteed statistical distribution properties sufficient for many real life applications and simple machinery. Initial computer simulations on this construction show promising results in the quality of the output and the computational resources in terms of required memory and complexity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02251v1-abstract-full').style.display = 'none'; document.getElementById('2404.02251v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01265">arXiv:2404.01265</a> <span> [<a href="https://arxiv.org/pdf/2404.01265">pdf</a>, <a href="https://arxiv.org/format/2404.01265">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Review of Distributed Quantum Computing. From single QPU to High Performance Quantum Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Barral%2C+D">David Barral</a>, <a href="/search/cs?searchtype=author&query=Cardama%2C+F+J">F. Javier Cardama</a>, <a href="/search/cs?searchtype=author&query=D%C3%ADaz%2C+G">Guillermo D铆az</a>, <a href="/search/cs?searchtype=author&query=Fa%C3%ADlde%2C+D">Daniel Fa铆lde</a>, <a href="/search/cs?searchtype=author&query=Llovo%2C+I+F">Iago F. Llovo</a>, <a href="/search/cs?searchtype=author&query=Juane%2C+M+M">Mariamo Mussa Juane</a>, <a href="/search/cs?searchtype=author&query=V%C3%A1zquez-P%C3%A9rez%2C+J">Jorge V谩zquez-P茅rez</a>, <a href="/search/cs?searchtype=author&query=Villasuso%2C+J">Juan Villasuso</a>, <a href="/search/cs?searchtype=author&query=Pi%C3%B1eiro%2C+C">C茅sar Pi帽eiro</a>, <a href="/search/cs?searchtype=author&query=Costas%2C+N">Natalia Costas</a>, <a href="/search/cs?searchtype=author&query=Pichel%2C+J+C">Juan C. Pichel</a>, <a href="/search/cs?searchtype=author&query=Pena%2C+T+F">Tom谩s F. Pena</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.01265v1-abstract-short" style="display: inline;"> The emerging field of quantum computing has shown it might change how we process information by using the unique principles of quantum mechanics. As researchers continue to push the boundaries of quantum technologies to unprecedented levels, distributed quantum computing raises as an obvious path to explore with the aim of boosting the computational power of current quantum systems. This paper pre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01265v1-abstract-full').style.display = 'inline'; document.getElementById('2404.01265v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01265v1-abstract-full" style="display: none;"> The emerging field of quantum computing has shown it might change how we process information by using the unique principles of quantum mechanics. As researchers continue to push the boundaries of quantum technologies to unprecedented levels, distributed quantum computing raises as an obvious path to explore with the aim of boosting the computational power of current quantum systems. This paper presents a comprehensive survey of the current state of the art in the distributed quantum computing field, exploring its foundational principles, landscape of achievements, challenges, and promising directions for further research. From quantum communication protocols to entanglement-based distributed algorithms, each aspect contributes to the mosaic of distributed quantum computing, making it an attractive approach to address the limitations of classical computing. Our objective is to provide an exhaustive overview for experienced researchers and field newcomers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01265v1-abstract-full').style.display = 'none'; document.getElementById('2404.01265v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.18204">arXiv:2402.18204</a> <span> [<a href="https://arxiv.org/pdf/2402.18204">pdf</a>, <a href="https://arxiv.org/format/2402.18204">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> ConvDTW-ACS: Audio Segmentation for Track Type Detection During Car Manufacturing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=L%C3%B3pez-Chilet%2C+%C3%81">脕lvaro L贸pez-Chilet</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhaoyi Liu</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+J+A">Jon Ander G贸mez</a>, <a href="/search/cs?searchtype=author&query=Alvarez%2C+C">Carlos Alvarez</a>, <a href="/search/cs?searchtype=author&query=Ortiz%2C+M+A">Marivi Alonso Ortiz</a>, <a href="/search/cs?searchtype=author&query=Mesa%2C+A+O">Andres Orejuela Mesa</a>, <a href="/search/cs?searchtype=author&query=Newton%2C+D">David Newton</a>, <a href="/search/cs?searchtype=author&query=Wolf-Monheim%2C+F">Friedrich Wolf-Monheim</a>, <a href="/search/cs?searchtype=author&query=Michiels%2C+S">Sam Michiels</a>, <a href="/search/cs?searchtype=author&query=Hughes%2C+D">Danny Hughes</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.18204v1-abstract-short" style="display: inline;"> This paper proposes a method for Acoustic Constrained Segmentation (ACS) in audio recordings of vehicles driven through a production test track, delimiting the boundaries of surface types in the track. ACS is a variant of classical acoustic segmentation where the sequence of labels is known, contiguous and invariable, which is especially useful in this work as the test track has a standard configu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18204v1-abstract-full').style.display = 'inline'; document.getElementById('2402.18204v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.18204v1-abstract-full" style="display: none;"> This paper proposes a method for Acoustic Constrained Segmentation (ACS) in audio recordings of vehicles driven through a production test track, delimiting the boundaries of surface types in the track. ACS is a variant of classical acoustic segmentation where the sequence of labels is known, contiguous and invariable, which is especially useful in this work as the test track has a standard configuration of surface types. The proposed ConvDTW-ACS method utilizes a Convolutional Neural Network for classifying overlapping image chunks extracted from the full audio spectrogram. Then, our custom Dynamic Time Warping algorithm aligns the sequence of predicted probabilities to the sequence of surface types in the track, from which timestamps of the surface type boundaries can be extracted. The method was evaluated on a real-world dataset collected from the Ford Manufacturing Plant in Valencia (Spain), achieving a mean error of 166 milliseconds when delimiting, within the audio, the boundaries of the surfaces in the track. The results demonstrate the effectiveness of the proposed method in accurately segmenting different surface types, which could enable the development of more specialized AI systems to improve the quality inspection process. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18204v1-abstract-full').style.display = 'none'; document.getElementById('2402.18204v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.01797">arXiv:2402.01797</a> <span> [<a href="https://arxiv.org/pdf/2402.01797">pdf</a>, <a href="https://arxiv.org/format/2402.01797">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</span> </div> </div> <p class="title is-5 mathjax"> Robust support vector machines via conic optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cepeda%2C+V">Valentina Cepeda</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a>, <a href="/search/cs?searchtype=author&query=Han%2C+S">Shaoning Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.01797v1-abstract-short" style="display: inline;"> We consider the problem of learning support vector machines robust to uncertainty. It has been established in the literature that typical loss functions, including the hinge loss, are sensible to data perturbations and outliers, thus performing poorly in the setting considered. In contrast, using the 0-1 loss or a suitable non-convex approximation results in robust estimators, at the expense of la… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01797v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01797v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01797v1-abstract-full" style="display: none;"> We consider the problem of learning support vector machines robust to uncertainty. It has been established in the literature that typical loss functions, including the hinge loss, are sensible to data perturbations and outliers, thus performing poorly in the setting considered. In contrast, using the 0-1 loss or a suitable non-convex approximation results in robust estimators, at the expense of large computational costs. In this paper we use mixed-integer optimization techniques to derive a new loss function that better approximates the 0-1 loss compared with existing alternatives, while preserving the convexity of the learning problem. In our computational results, we show that the proposed estimator is competitive with the standard SVMs with the hinge loss in outlier-free regimes and better in the presence of outliers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01797v1-abstract-full').style.display = 'none'; document.getElementById('2402.01797v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.12251">arXiv:2401.12251</a> <span> [<a href="https://arxiv.org/pdf/2401.12251">pdf</a>, <a href="https://arxiv.org/format/2401.12251">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Diffusion Representation for Asymmetric Kernels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gomez%2C+A+A">Alvaro Almeida Gomez</a>, <a href="/search/cs?searchtype=author&query=Neto%2C+A+S">Antonio Silva Neto</a>, <a href="/search/cs?searchtype=author&query=zubelli%2C+J">Jorge zubelli</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.12251v1-abstract-short" style="display: inline;"> We extend the diffusion-map formalism to data sets that are induced by asymmetric kernels. Analytical convergence results of the resulting expansion are proved, and an algorithm is proposed to perform the dimensional reduction. In this work we study data sets in which its geometry structure is induced by an asymmetric kernel. We use a priori coordinate system to represent this geometry and, thus,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.12251v1-abstract-full').style.display = 'inline'; document.getElementById('2401.12251v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.12251v1-abstract-full" style="display: none;"> We extend the diffusion-map formalism to data sets that are induced by asymmetric kernels. Analytical convergence results of the resulting expansion are proved, and an algorithm is proposed to perform the dimensional reduction. In this work we study data sets in which its geometry structure is induced by an asymmetric kernel. We use a priori coordinate system to represent this geometry and, thus, be able to improve the computational complexity of reducing the dimensionality of data sets. A coordinate system connected to the tensor product of Fourier basis is used to represent the underlying geometric structure obtained by the diffusion-map, thus reducing the dimensionality of the data set and making use of the speedup provided by the two-dimensional Fast Fourier Transform algorithm (2-D FFT). We compare our results with those obtained by other eigenvalue expansions, and verify the efficiency of the algorithms with synthetic data, as well as with real data from applications including climate change studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.12251v1-abstract-full').style.display = 'none'; document.getElementById('2401.12251v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Applied Numerical Mathematics, 2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.10304">arXiv:2401.10304</a> <span> [<a href="https://arxiv.org/pdf/2401.10304">pdf</a>, <a href="https://arxiv.org/format/2401.10304">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> On the Readiness of Scientific Data for a Fair and Transparent Use in Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Giner-Miguelez%2C+J">Joan Giner-Miguelez</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Abel G贸mez</a>, <a href="/search/cs?searchtype=author&query=Cabot%2C+J">Jordi Cabot</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.10304v2-abstract-short" style="display: inline;"> To ensure the fairness and trustworthiness of machine learning (ML) systems, recent legislative initiatives and relevant research in the ML community have pointed out the need to document the data used to train ML models. Besides, data-sharing practices in many scientific domains have evolved in recent years for reproducibility purposes. In this sense, academic institutions' adoption of these prac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.10304v2-abstract-full').style.display = 'inline'; document.getElementById('2401.10304v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.10304v2-abstract-full" style="display: none;"> To ensure the fairness and trustworthiness of machine learning (ML) systems, recent legislative initiatives and relevant research in the ML community have pointed out the need to document the data used to train ML models. Besides, data-sharing practices in many scientific domains have evolved in recent years for reproducibility purposes. In this sense, academic institutions' adoption of these practices has encouraged researchers to publish their data and technical documentation in peer-reviewed publications such as data papers. In this study, we analyze how this broader scientific data documentation meets the needs of the ML community and regulatory bodies for its use in ML technologies. We examine a sample of 4041 data papers of different domains, assessing their completeness, coverage of the requested dimensions, and trends in recent years. We focus on the most and least documented dimensions and compare the results with those of an ML-focused venue (NeurIPS D&B track) publishing papers describing datasets. As a result, we propose a set of recommendation guidelines for data creators and scientific data publishers to increase their data's preparedness for its transparent and fairer use in ML technologies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.10304v2-abstract-full').style.display = 'none'; document.getElementById('2401.10304v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.20671">arXiv:2310.20671</a> <span> [<a href="https://arxiv.org/pdf/2310.20671">pdf</a>, <a href="https://arxiv.org/format/2310.20671">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1088/2632-2153/ad9431">10.1088/2632-2153/ad9431 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Viqueira%2C+J+D">Jos茅 Daniel Viqueira</a>, <a href="/search/cs?searchtype=author&query=Fa%C3%ADlde%2C+D">Daniel Fa铆lde</a>, <a href="/search/cs?searchtype=author&query=Juane%2C+M+M">Mariamo M. Juane</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a>, <a href="/search/cs?searchtype=author&query=Mera%2C+D">David Mera</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.20671v2-abstract-short" style="display: inline;"> Quantum Recurrent Neural Networks (QRNNs) are robust candidates for modelling and predicting future values in multivariate time series. However, the effective implementation of some QRNN models is limited by the need for mid-circuit measurements. Those increase the requirements for quantum hardware, which in the current NISQ era does not allow reliable computations. Emulation arises as the main ne… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.20671v2-abstract-full').style.display = 'inline'; document.getElementById('2310.20671v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.20671v2-abstract-full" style="display: none;"> Quantum Recurrent Neural Networks (QRNNs) are robust candidates for modelling and predicting future values in multivariate time series. However, the effective implementation of some QRNN models is limited by the need for mid-circuit measurements. Those increase the requirements for quantum hardware, which in the current NISQ era does not allow reliable computations. Emulation arises as the main near-term alternative to explore the potential of QRNNs, but existing quantum emulators are not dedicated to circuits with multiple intermediate measurements. In this context, we design a specific emulation method that relies on density matrix formalism. Using a compact tensor notation, we provide the mathematical formulation of the operator-sum representation involved. This allows us to show how the present and past information from a time series is transmitted through the circuit, and how to reduce the computational cost in every time step of the emulated network. In addition, we derive the analytical gradient and the Hessian of the network outputs with respect to its trainable parameters, which are needed when the outputs have stochastic noise due to hardware errors and a finite number of circuit shots (sampling). We finally test the presented methods using a hardware-efficient ansatz and four diverse datasets that include univariate and multivariate time series, with and without sampling noise. In addition, we compare the model with other existing quantum and classical approaches. Our results show how QRNNs can be trained with numerical and analytical gradients to make accurate predictions of future values by capturing non-trivial patterns of input series with different complexities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.20671v2-abstract-full').style.display = 'none'; document.getElementById('2310.20671v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 8 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Mach. Learn.: Sci. Technol. 6, 015023 (2025) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.17772">arXiv:2310.17772</a> <span> [<a href="https://arxiv.org/pdf/2310.17772">pdf</a>, <a href="https://arxiv.org/format/2310.17772">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Learning Optimal Classification Trees Robust to Distribution Shifts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Justin%2C+N">Nathan Justin</a>, <a href="/search/cs?searchtype=author&query=Aghaei%2C+S">Sina Aghaei</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a>, <a href="/search/cs?searchtype=author&query=Vayanos%2C+P">Phebe Vayanos</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.17772v1-abstract-short" style="display: inline;"> We consider the problem of learning classification trees that are robust to distribution shifts between training and testing/deployment data. This problem arises frequently in high stakes settings such as public health and social work where data is often collected using self-reported surveys which are highly sensitive to e.g., the framing of the questions, the time when and place where the survey… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17772v1-abstract-full').style.display = 'inline'; document.getElementById('2310.17772v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.17772v1-abstract-full" style="display: none;"> We consider the problem of learning classification trees that are robust to distribution shifts between training and testing/deployment data. This problem arises frequently in high stakes settings such as public health and social work where data is often collected using self-reported surveys which are highly sensitive to e.g., the framing of the questions, the time when and place where the survey is conducted, and the level of comfort the interviewee has in sharing information with the interviewer. We propose a method for learning optimal robust classification trees based on mixed-integer robust optimization technology. In particular, we demonstrate that the problem of learning an optimal robust tree can be cast as a single-stage mixed-integer robust optimization problem with a highly nonlinear and discontinuous objective. We reformulate this problem equivalently as a two-stage linear robust optimization problem for which we devise a tailored solution procedure based on constraint generation. We evaluate the performance of our approach on numerous publicly available datasets, and compare the performance to a regularized, non-robust optimal tree. We show an increase of up to 12.48% in worst-case accuracy and of up to 4.85% in average-case accuracy across several datasets and distribution shifts from using our robust solution in comparison to the non-robust one. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17772v1-abstract-full').style.display = 'none'; document.getElementById('2310.17772v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">47 pages, 11 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.02292">arXiv:2309.02292</a> <span> [<a href="https://arxiv.org/pdf/2309.02292">pdf</a>, <a href="https://arxiv.org/format/2309.02292">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Disordered Systems and Neural Networks">cond-mat.dis-nn</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistical Mechanics">cond-mat.stat-mech</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.21468/SciPostPhys.16.4.095">10.21468/SciPostPhys.16.4.095 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Inferring effective couplings with Restricted Boltzmann Machines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Decelle%2C+A">Aur茅lien Decelle</a>, <a href="/search/cs?searchtype=author&query=Furtlehner%2C+C">Cyril Furtlehner</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A+D+J+N">Alfonso De Jesus Navas G贸mez</a>, <a href="/search/cs?searchtype=author&query=Seoane%2C+B">Beatriz Seoane</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.02292v3-abstract-short" style="display: inline;"> Generative models offer a direct way of modeling complex data. Energy-based models attempt to encode the statistical correlations observed in the data at the level of the Boltzmann weight associated with an energy function in the form of a neural network. We address here the challenge of understanding the physical interpretation of such models. In this study, we propose a simple solution by implem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02292v3-abstract-full').style.display = 'inline'; document.getElementById('2309.02292v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.02292v3-abstract-full" style="display: none;"> Generative models offer a direct way of modeling complex data. Energy-based models attempt to encode the statistical correlations observed in the data at the level of the Boltzmann weight associated with an energy function in the form of a neural network. We address here the challenge of understanding the physical interpretation of such models. In this study, we propose a simple solution by implementing a direct mapping between the Restricted Boltzmann Machine and an effective Ising spin Hamiltonian. This mapping includes interactions of all possible orders, going beyond the conventional pairwise interactions typically considered in the inverse Ising (or Boltzmann Machine) approach, and allowing the description of complex datasets. Earlier works attempted to achieve this goal, but the proposed mappings were inaccurate for inference applications, did not properly treat the complexity of the problem, or did not provide precise prescriptions for practical application. To validate our method, we performed several controlled inverse numerical experiments in which we trained the RBMs using equilibrium samples of predefined models with local external fields, 2-body and 3-body interactions in different sparse topologies. The results demonstrate the effectiveness of our proposed approach in learning the correct interaction network and pave the way for its application in modeling interesting binary variable datasets. We also evaluate the quality of the inferred model based on different training methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02292v3-abstract-full').style.display = 'none'; document.getElementById('2309.02292v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 figures, 39 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> SciPost Phys. 16, 095 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.16767">arXiv:2308.16767</a> <span> [<a href="https://arxiv.org/pdf/2308.16767">pdf</a>, <a href="https://arxiv.org/format/2308.16767">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Reinforcement learning for safety-critical control of an automated vehicle </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thaler%2C+F">Florian Thaler</a>, <a href="/search/cs?searchtype=author&query=Rammerstorfer%2C+F">Franz Rammerstorfer</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+J+A">Jon Ander Gomez</a>, <a href="/search/cs?searchtype=author&query=Crespo%2C+R+G">Raul Garcia Crespo</a>, <a href="/search/cs?searchtype=author&query=Pasqual%2C+L">Leticia Pasqual</a>, <a href="/search/cs?searchtype=author&query=Postl%2C+M">Markus Postl</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.16767v1-abstract-short" style="display: inline;"> We present our approach for the development, validation and deployment of a data-driven decision-making function for the automated control of a vehicle. The decisionmaking function, based on an artificial neural network is trained to steer the mobile robot SPIDER towards a predefined, static path to a target point while avoiding collisions with obstacles along the path. The training is conducted b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.16767v1-abstract-full').style.display = 'inline'; document.getElementById('2308.16767v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.16767v1-abstract-full" style="display: none;"> We present our approach for the development, validation and deployment of a data-driven decision-making function for the automated control of a vehicle. The decisionmaking function, based on an artificial neural network is trained to steer the mobile robot SPIDER towards a predefined, static path to a target point while avoiding collisions with obstacles along the path. The training is conducted by means of proximal policy optimisation (PPO), a state of the art algorithm from the field of reinforcement learning. The resulting controller is validated using KPIs quantifying its capability to follow a given path and its reactivity on perceived obstacles along the path. The corresponding tests are carried out in the training environment. Additionally, the tests shall be performed as well in the robotics situation Gazebo and in real world scenarios. For the latter the controller is deployed on a FPGA-based development platform, the FRACTAL platform, and integrated into the SPIDER software stack. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.16767v1-abstract-full').style.display = 'none'; document.getElementById('2308.16767v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.03554">arXiv:2308.03554</a> <span> [<a href="https://arxiv.org/pdf/2308.03554">pdf</a>, <a href="https://arxiv.org/format/2308.03554">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> TemporalFED: Detecting Cyberattacks in Industrial Time-Series Data Using Decentralized Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+%C3%81+L+P">脕ngel Luis Perales G贸mez</a>, <a href="/search/cs?searchtype=author&query=Beltr%C3%A1n%2C+E+T+M">Enrique Tom谩s Mart铆nez Beltr谩n</a>, <a href="/search/cs?searchtype=author&query=S%C3%A1nchez%2C+P+M+S">Pedro Miguel S谩nchez S谩nchez</a>, <a href="/search/cs?searchtype=author&query=Celdr%C3%A1n%2C+A+H">Alberto Huertas Celdr谩n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.03554v1-abstract-short" style="display: inline;"> Industry 4.0 has brought numerous advantages, such as increasing productivity through automation. However, it also presents major cybersecurity issues such as cyberattacks affecting industrial processes. Federated Learning (FL) combined with time-series analysis is a promising cyberattack detection mechanism proposed in the literature. However, the fact of having a single point of failure and netw… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03554v1-abstract-full').style.display = 'inline'; document.getElementById('2308.03554v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.03554v1-abstract-full" style="display: none;"> Industry 4.0 has brought numerous advantages, such as increasing productivity through automation. However, it also presents major cybersecurity issues such as cyberattacks affecting industrial processes. Federated Learning (FL) combined with time-series analysis is a promising cyberattack detection mechanism proposed in the literature. However, the fact of having a single point of failure and network bottleneck are critical challenges that need to be tackled. Thus, this article explores the benefits of the Decentralized Federated Learning (DFL) in terms of cyberattack detection and resource consumption. The work presents TemporalFED, a software module for detecting anomalies in industrial environments using FL paradigms and time series. TemporalFED incorporates three components: Time Series Conversion, Feature Engineering, and Time Series Stationary Conversion. To evaluate TemporalFED, it was deployed on Fedstellar, a DFL framework. Then, a pool of experiments measured the detection performance and resource consumption in a chemical gas industrial environment with different time-series configurations, FL paradigms, and topologies. The results showcase the superiority of the configuration utilizing DFL and Semi-Decentralized Federated Learning (SDFL) paradigms, along with a fully connected topology, which achieved the best performance in anomaly detection. Regarding resource consumption, the configuration without feature engineering employed less bandwidth, CPU, and RAM than other configurations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03554v1-abstract-full').style.display = 'none'; document.getElementById('2308.03554v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15691">arXiv:2307.15691</a> <span> [<a href="https://arxiv.org/pdf/2307.15691">pdf</a>, <a href="https://arxiv.org/format/2307.15691">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> ODTlearn: A Package for Learning Optimal Decision Trees for Prediction and Prescription </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vossler%2C+P">Patrick Vossler</a>, <a href="/search/cs?searchtype=author&query=Aghaei%2C+S">Sina Aghaei</a>, <a href="/search/cs?searchtype=author&query=Justin%2C+N">Nathan Justin</a>, <a href="/search/cs?searchtype=author&query=Jo%2C+N">Nathanael Jo</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a>, <a href="/search/cs?searchtype=author&query=Vayanos%2C+P">Phebe Vayanos</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.15691v2-abstract-short" style="display: inline;"> ODTLearn is an open-source Python package that provides methods for learning optimal decision trees for high-stakes predictive and prescriptive tasks based on the mixed-integer optimization (MIO) framework proposed in Aghaei et al. (2019) and several of its extensions. The current version of the package provides implementations for learning optimal classification trees, optimal fair classification… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15691v2-abstract-full').style.display = 'inline'; document.getElementById('2307.15691v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15691v2-abstract-full" style="display: none;"> ODTLearn is an open-source Python package that provides methods for learning optimal decision trees for high-stakes predictive and prescriptive tasks based on the mixed-integer optimization (MIO) framework proposed in Aghaei et al. (2019) and several of its extensions. The current version of the package provides implementations for learning optimal classification trees, optimal fair classification trees, optimal classification trees robust to distribution shifts, and optimal prescriptive trees from observational data. We have designed the package to be easy to maintain and extend as new optimal decision tree problem classes, reformulation strategies, and solution algorithms are introduced. To this end, the package follows object-oriented design principles and supports both commercial (Gurobi) and open source (COIN-OR branch and cut) solvers. The package documentation and an extensive user guide can be found at https://d3m-research-group.github.io/odtlearn/. Additionally, users can view the package source code and submit feature requests and bug reports by visiting https://github.com/D3M-Research-Group/odtlearn. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15691v2-abstract-full').style.display = 'none'; document.getElementById('2307.15691v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.13750">arXiv:2307.13750</a> <span> [<a href="https://arxiv.org/pdf/2307.13750">pdf</a>, <a href="https://arxiv.org/format/2307.13750">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Solution Path of Time-varying Markov Random Fields with Discrete Regularization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fattahi%2C+S">Salar Fattahi</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Andres Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.13750v1-abstract-short" style="display: inline;"> We study the problem of inferring sparse time-varying Markov random fields (MRFs) with different discrete and temporal regularizations on the parameters. Due to the intractability of discrete regularization, most approaches for solving this problem rely on the so-called maximum-likelihood estimation (MLE) with relaxed regularization, which neither results in ideal statistical properties nor scale… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.13750v1-abstract-full').style.display = 'inline'; document.getElementById('2307.13750v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.13750v1-abstract-full" style="display: none;"> We study the problem of inferring sparse time-varying Markov random fields (MRFs) with different discrete and temporal regularizations on the parameters. Due to the intractability of discrete regularization, most approaches for solving this problem rely on the so-called maximum-likelihood estimation (MLE) with relaxed regularization, which neither results in ideal statistical properties nor scale to the dimensions encountered in realistic settings. In this paper, we address these challenges by departing from the MLE paradigm and resorting to a new class of constrained optimization problems with exact, discrete regularization to promote sparsity in the estimated parameters. Despite the nonconvex and discrete nature of our formulation, we show that it can be solved efficiently and parametrically for all sparsity levels. More specifically, we show that the entire solution path of the time-varying MRF for all sparsity levels can be obtained in $\mathcal{O}(pT^3)$, where $T$ is the number of time steps and $p$ is the number of unknown parameters at any given time. The efficient and parametric characterization of the solution path renders our approach highly suitable for cross-validation, where parameter estimation is required for varying regularization values. Despite its simplicity and efficiency, we show that our proposed approach achieves provably small estimation error for different classes of time-varying MRFs, namely Gaussian and discrete MRFs, with as few as one sample per time. Utilizing our algorithm, we can recover the complete solution path for instances of time-varying MRFs featuring over 30 million variables in less than 12 minutes on a standard laptop computer. Our code is available at \url{https://sites.google.com/usc.edu/gomez/data}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.13750v1-abstract-full').style.display = 'none'; document.getElementById('2307.13750v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.05975">arXiv:2307.05975</a> <span> [<a href="https://arxiv.org/pdf/2307.05975">pdf</a>, <a href="https://arxiv.org/format/2307.05975">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Outlier detection in regression: conic quadratic formulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a>, <a href="/search/cs?searchtype=author&query=Neto%2C+J">Jos茅 Neto</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.05975v1-abstract-short" style="display: inline;"> In many applications, when building linear regression models, it is important to account for the presence of outliers, i.e., corrupted input data points. Such problems can be formulated as mixed-integer optimization problems involving cubic terms, each given by the product of a binary variable and a quadratic term of the continuous variables. Existing approaches in the literature, typically relyin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.05975v1-abstract-full').style.display = 'inline'; document.getElementById('2307.05975v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.05975v1-abstract-full" style="display: none;"> In many applications, when building linear regression models, it is important to account for the presence of outliers, i.e., corrupted input data points. Such problems can be formulated as mixed-integer optimization problems involving cubic terms, each given by the product of a binary variable and a quadratic term of the continuous variables. Existing approaches in the literature, typically relying on the linearization of the cubic terms using big-M constraints, suffer from weak relaxation and poor performance in practice. In this work we derive stronger second-order conic relaxations that do not involve big-M constraints. Our computational experiments indicate that the proposed formulations are several orders-of-magnitude faster than existing big-M formulations in the literature for this problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.05975v1-abstract-full').style.display = 'none'; document.getElementById('2307.05975v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.02997">arXiv:2307.02997</a> <span> [<a href="https://arxiv.org/pdf/2307.02997">pdf</a>, <a href="https://arxiv.org/format/2307.02997">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Fourier-Net+: Leveraging Band-Limited Representation for Efficient 3D Medical Image Registration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xi Jia</a>, <a href="/search/cs?searchtype=author&query=Thorley%2C+A">Alexander Thorley</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+W">Wenqi Lu</a>, <a href="/search/cs?searchtype=author&query=Kotecha%2C+D">Dipak Kotecha</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+J">Jinming Duan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.02997v1-abstract-short" style="display: inline;"> U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields, which for high-resolution volumetric image data is a resource-intensive and time-consuming task. To tackle this challenge, we first propose Fourier-Net, which replaces the costly U-Net style expansive path with a parameter-free model-driven decoder. Instead of directly predicting a f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02997v1-abstract-full').style.display = 'inline'; document.getElementById('2307.02997v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.02997v1-abstract-full" style="display: none;"> U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields, which for high-resolution volumetric image data is a resource-intensive and time-consuming task. To tackle this challenge, we first propose Fourier-Net, which replaces the costly U-Net style expansive path with a parameter-free model-driven decoder. Instead of directly predicting a full-resolution displacement field, our Fourier-Net learns a low-dimensional representation of the displacement field in the band-limited Fourier domain which our model-driven decoder converts to a full-resolution displacement field in the spatial domain. Expanding upon Fourier-Net, we then introduce Fourier-Net+, which additionally takes the band-limited spatial representation of the images as input and further reduces the number of convolutional layers in the U-Net style network's contracting path. Finally, to enhance the registration performance, we propose a cascaded version of Fourier-Net+. We evaluate our proposed methods on three datasets, on which our proposed Fourier-Net and its variants achieve comparable results with current state-of-the art methods, while exhibiting faster inference speeds, lower memory footprint, and fewer multiply-add operations. With such small computational cost, our Fourier-Net+ enables the efficient training of large-scale 3D registration on low-VRAM GPUs. Our code is publicly available at \url{https://github.com/xi-jia/Fourier-Net}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.02997v1-abstract-full').style.display = 'none'; document.getElementById('2307.02997v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under review. arXiv admin note: text overlap with arXiv:2211.16342</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.15414">arXiv:2306.15414</a> <span> [<a href="https://arxiv.org/pdf/2306.15414">pdf</a>, <a href="https://arxiv.org/format/2306.15414">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> FAIR EVA: Bringing institutional multidisciplinary repositories into the FAIR picture </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+F+A">Fernando Aguilar G贸mez</a>, <a href="/search/cs?searchtype=author&query=Bernal%2C+I">Isabel Bernal</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.15414v1-abstract-short" style="display: inline;"> The FAIR Principles are a set of good practices to improve the reproducibility and quality of data in an Open Science context. Different sets of indicators have been proposed to evaluate the FAIRness of digital objects, including datasets that are usually stored in repositories or data portals. However, indicators like those proposed by the Research Data Alliance are provided from a high-level per… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.15414v1-abstract-full').style.display = 'inline'; document.getElementById('2306.15414v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.15414v1-abstract-full" style="display: none;"> The FAIR Principles are a set of good practices to improve the reproducibility and quality of data in an Open Science context. Different sets of indicators have been proposed to evaluate the FAIRness of digital objects, including datasets that are usually stored in repositories or data portals. However, indicators like those proposed by the Research Data Alliance are provided from a high-level perspective that can be interpreted and they are not always realistic to particular environments like multidisciplinary repositories. This paper describes FAIR EVA, a new tool developed within the European Open Science Cloud context that is oriented to particular data management systems like open repositories, which can be customized to a specific case in a scalable and automatic environment. It aims to be adaptive enough to work for different environments, repository software and disciplines, taking into account the flexibility of the FAIR Principles. As an example, we present DIGITAL.CSIC repository as the first target of the tool, gathering the particular needs of a multidisciplinary institution as well as its institutional repository. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.15414v1-abstract-full').style.display = 'none'; document.getElementById('2306.15414v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.14851">arXiv:2306.14851</a> <span> [<a href="https://arxiv.org/pdf/2306.14851">pdf</a>, <a href="https://arxiv.org/format/2306.14851">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Stability-Adjusted Cross-Validation for Sparse Linear Regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cory-Wright%2C+R">Ryan Cory-Wright</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Andr茅s G贸mez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.14851v2-abstract-short" style="display: inline;"> Given a high-dimensional covariate matrix and a response vector, ridge-regularized sparse linear regression selects a subset of features that explains the relationship between covariates and the response in an interpretable manner. To select the sparsity and robustness of linear regressors, techniques like k-fold cross-validation are commonly used for hyperparameter tuning. However, cross-validati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.14851v2-abstract-full').style.display = 'inline'; document.getElementById('2306.14851v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.14851v2-abstract-full" style="display: none;"> Given a high-dimensional covariate matrix and a response vector, ridge-regularized sparse linear regression selects a subset of features that explains the relationship between covariates and the response in an interpretable manner. To select the sparsity and robustness of linear regressors, techniques like k-fold cross-validation are commonly used for hyperparameter tuning. However, cross-validation substantially increases the computational cost of sparse regression as it requires solving many mixed-integer optimization problems (MIOs). Additionally, validation metrics often serve as noisy estimators of test set errors, with different hyperparameter combinations leading to models with different noise levels. Therefore, optimizing over these metrics is vulnerable to out-of-sample disappointment, especially in underdetermined settings. To improve upon this state of affairs, we make two key contributions. First, motivated by the generalization theory literature, we propose selecting hyperparameters that minimize a weighted sum of a cross-validation metric and a model's output stability, thus reducing the risk of poor out-of-sample performance. Second, we leverage ideas from the mixed-integer optimization literature to obtain computationally tractable relaxations of k-fold cross-validation metrics and the output stability of regressors, facilitating hyperparameter selection after solving fewer MIOs. These relaxations result in an efficient cyclic coordinate descent scheme, achieving lower validation errors than via traditional methods such as grid search. On synthetic datasets, our confidence adjustment procedure improves out-of-sample performance by 2%-5% compared to minimizing the k-fold error alone. On 13 real-world datasets, our confidence adjustment procedure reduces test set error by 2%, on average. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.14851v2-abstract-full').style.display = 'none'; document.getElementById('2306.14851v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Updated paper, including generalization to k-fold cross-validation and a new title</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.09750">arXiv:2306.09750</a> <span> [<a href="https://arxiv.org/pdf/2306.09750">pdf</a>, <a href="https://arxiv.org/format/2306.09750">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.eswa.2023.122861">10.1016/j.eswa.2023.122861 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fedstellar: A Platform for Decentralized Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Beltr%C3%A1n%2C+E+T+M">Enrique Tom谩s Mart铆nez Beltr谩n</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+%C3%81+L+P">脕ngel Luis Perales G贸mez</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+C">Chao Feng</a>, <a href="/search/cs?searchtype=author&query=S%C3%A1nchez%2C+P+M+S">Pedro Miguel S谩nchez S谩nchez</a>, <a href="/search/cs?searchtype=author&query=Bernal%2C+S+L">Sergio L贸pez Bernal</a>, <a href="/search/cs?searchtype=author&query=Bovet%2C+G">G茅r么me Bovet</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez%2C+M+G">Manuel Gil P茅rez</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez%2C+G+M">Gregorio Mart铆nez P茅rez</a>, <a href="/search/cs?searchtype=author&query=Celdr%C3%A1n%2C+A+H">Alberto Huertas Celdr谩n</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.09750v4-abstract-short" style="display: inline;"> In 2016, Google proposed Federated Learning (FL) as a novel paradigm to train Machine Learning (ML) models across the participants of a federation while preserving data privacy. Since its birth, Centralized FL (CFL) has been the most used approach, where a central entity aggregates participants' models to create a global one. However, CFL presents limitations such as communication bottlenecks, sin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.09750v4-abstract-full').style.display = 'inline'; document.getElementById('2306.09750v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.09750v4-abstract-full" style="display: none;"> In 2016, Google proposed Federated Learning (FL) as a novel paradigm to train Machine Learning (ML) models across the participants of a federation while preserving data privacy. Since its birth, Centralized FL (CFL) has been the most used approach, where a central entity aggregates participants' models to create a global one. However, CFL presents limitations such as communication bottlenecks, single point of failure, and reliance on a central server. Decentralized Federated Learning (DFL) addresses these issues by enabling decentralized model aggregation and minimizing dependency on a central entity. Despite these advances, current platforms training DFL models struggle with key issues such as managing heterogeneous federation network topologies. To overcome these challenges, this paper presents Fedstellar, a platform extended from p2pfl library and designed to train FL models in a decentralized, semi-decentralized, and centralized fashion across diverse federations of physical or virtualized devices. The Fedstellar implementation encompasses a web application with an interactive graphical interface, a controller for deploying federations of nodes using physical or virtual devices, and a core deployed on each device which provides the logic needed to train, aggregate, and communicate in the network. The effectiveness of the platform has been demonstrated in two scenarios: a physical deployment involving single-board devices such as Raspberry Pis for detecting cyberattacks, and a virtualized deployment comparing various FL approaches in a controlled environment using MNIST and CIFAR-10 datasets. In both scenarios, Fedstellar demonstrated consistent performance and adaptability, achieving F1 scores of 91%, 98%, and 91.2% using DFL for detecting cyberattacks and classifying MNIST and CIFAR-10, respectively, reducing training time by 32% compared to centralized approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.09750v4-abstract-full').style.display = 'none'; document.getElementById('2306.09750v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.04739">arXiv:2306.04739</a> <span> [<a href="https://arxiv.org/pdf/2306.04739">pdf</a>, <a href="https://arxiv.org/format/2306.04739">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Automatic retrieval of corresponding US views in longitudinal examinations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kerdegari%2C+H">Hamideh Kerdegari</a>, <a href="/search/cs?searchtype=author&query=Phung1%2C+T+H+N">Tran Huy Nhat Phung1</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+V+H">Van Hao Nguyen</a>, <a href="/search/cs?searchtype=author&query=Truong%2C+T+P+T">Thi Phuong Thao Truong</a>, <a href="/search/cs?searchtype=author&query=Le%2C+N+M+T">Ngoc Minh Thu Le</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+P">Thanh Phuong Le</a>, <a href="/search/cs?searchtype=author&query=Le%2C+T+M+T">Thi Mai Thao Le</a>, <a href="/search/cs?searchtype=author&query=Pisani%2C+L">Luigi Pisani</a>, <a href="/search/cs?searchtype=author&query=Denehy%2C+L">Linda Denehy</a>, <a href="/search/cs?searchtype=author&query=Consortium%2C+V">Vital Consortium</a>, <a href="/search/cs?searchtype=author&query=Razavi%2C+R">Reza Razavi</a>, <a href="/search/cs?searchtype=author&query=Thwaites%2C+L">Louise Thwaites</a>, <a href="/search/cs?searchtype=author&query=Yacoub%2C+S">Sophie Yacoub</a>, <a href="/search/cs?searchtype=author&query=King%2C+A+P">Andrew P. King</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.04739v1-abstract-short" style="display: inline;"> Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed. Muscle mass must be recovered through physiotherapy before patient discharge and ultrasound imaging is frequently used to assess the recovery process by measuring the muscle size over time. However, these manual measurements are subject to large variability, par… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.04739v1-abstract-full').style.display = 'inline'; document.getElementById('2306.04739v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.04739v1-abstract-full" style="display: none;"> Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed. Muscle mass must be recovered through physiotherapy before patient discharge and ultrasound imaging is frequently used to assess the recovery process by measuring the muscle size over time. However, these manual measurements are subject to large variability, particularly since the scans are typically acquired on different days and potentially by different operators. In this paper, we propose a self-supervised contrastive learning approach to automatically retrieve similar ultrasound muscle views at different scan times. Three different models were compared using data from 67 patients acquired in the ICU. Results indicate that our contrastive model outperformed a supervised baseline model in the task of view retrieval with an AUC of 73.52% and when combined with an automatic segmentation model achieved 5.7%+/-0.24% error in cross-sectional area. Furthermore, a user study survey confirmed the efficacy of our model for muscle view retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.04739v1-abstract-full').style.display = 'none'; document.getElementById('2306.04739v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.05424">arXiv:2305.05424</a> <span> [<a href="https://arxiv.org/pdf/2305.05424">pdf</a>, <a href="https://arxiv.org/format/2305.05424">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stojanovski%2C+D">David Stojanovski</a>, <a href="/search/cs?searchtype=author&query=Hermida%2C+U">Uxio Hermida</a>, <a href="/search/cs?searchtype=author&query=Lamata%2C+P">Pablo Lamata</a>, <a href="/search/cs?searchtype=author&query=Beqiri%2C+A">Arian Beqiri</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.05424v2-abstract-short" style="display: inline;"> We propose a novel pipeline for the generation of synthetic ultrasound images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for ultrasound image analysis tasks such as cardiac segmentation. To demonstrate the effectiveness of this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.05424v2-abstract-full').style.display = 'inline'; document.getElementById('2305.05424v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.05424v2-abstract-full" style="display: none;"> We propose a novel pipeline for the generation of synthetic ultrasound images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for ultrasound image analysis tasks such as cardiac segmentation. To demonstrate the effectiveness of this approach, we generated synthetic 2D echocardiograms and trained a neural network for segmenting the left ventricle and left atrium. The performance of the network trained on exclusively synthetic images was evaluated on an unseen dataset of real images and yielded mean Dice scores of 88.6 $\pm 4.91$ , 91.9 $\pm 4.22$, 85.2 $\pm 4.83$ \% for left ventricular endocardium, epicardium and left atrial segmentation respectively. This represents a relative increase of $9.2$, $3.3$ and $13.9$ \% in Dice scores compared to the previous state-of-the-art. The proposed pipeline has potential for application to a wide range of other tasks across various medical imaging modalities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.05424v2-abstract-full').style.display = 'none'; document.getElementById('2305.05424v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.03571">arXiv:2304.03571</a> <span> [<a href="https://arxiv.org/pdf/2304.03571">pdf</a>, <a href="https://arxiv.org/format/2304.03571">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Fluid Dynamics">physics.flu-dyn</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> $尾$-Variational autoencoders and transformers for reduced-order modelling of fluid flows </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Solera-Rico%2C+A">Alberto Solera-Rico</a>, <a href="/search/cs?searchtype=author&query=Vila%2C+C+S">Carlos Sanmiguel Vila</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+M+A">M. A. G贸mez</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yuning Wang</a>, <a href="/search/cs?searchtype=author&query=Almashjary%2C+A">Abdulrahman Almashjary</a>, <a href="/search/cs?searchtype=author&query=Dawson%2C+S+T+M">Scott T. M. Dawson</a>, <a href="/search/cs?searchtype=author&query=Vinuesa%2C+R">Ricardo Vinuesa</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.03571v2-abstract-short" style="display: inline;"> Variational autoencoder (VAE) architectures have the potential to develop reduced-order models (ROMs) for chaotic fluid flows. We propose a method for learning compact and near-orthogonal ROMs using a combination of a $尾$-VAE and a transformer, tested on numerical data from a two-dimensional viscous flow in both periodic and chaotic regimes. The $尾$-VAE is trained to learn a compact latent represe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.03571v2-abstract-full').style.display = 'inline'; document.getElementById('2304.03571v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.03571v2-abstract-full" style="display: none;"> Variational autoencoder (VAE) architectures have the potential to develop reduced-order models (ROMs) for chaotic fluid flows. We propose a method for learning compact and near-orthogonal ROMs using a combination of a $尾$-VAE and a transformer, tested on numerical data from a two-dimensional viscous flow in both periodic and chaotic regimes. The $尾$-VAE is trained to learn a compact latent representation of the flow velocity, and the transformer is trained to predict the temporal dynamics in latent space. Using the $尾$-VAE to learn disentangled representations in latent-space, we obtain a more interpretable flow model with features that resemble those observed in the proper orthogonal decomposition, but with a more efficient representation. Using Poincar茅 maps, the results show that our method can capture the underlying dynamics of the flow outperforming other prediction models. The proposed method has potential applications in other fields such as weather forecasting, structural dynamics or biomedical engineering. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.03571v2-abstract-full').style.display = 'none'; document.getElementById('2304.03571v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.12644">arXiv:2303.12644</a> <span> [<a href="https://arxiv.org/pdf/2303.12644">pdf</a>, <a href="https://arxiv.org/format/2303.12644">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-031-43999-5_14">10.1007/978-3-031-43999-5_14 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reynaud%2C+H">Hadrien Reynaud</a>, <a href="/search/cs?searchtype=author&query=Qiao%2C+M">Mengyun Qiao</a>, <a href="/search/cs?searchtype=author&query=Dombrowski%2C+M">Mischa Dombrowski</a>, <a href="/search/cs?searchtype=author&query=Day%2C+T">Thomas Day</a>, <a href="/search/cs?searchtype=author&query=Razavi%2C+R">Reza Razavi</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Leeson%2C+P">Paul Leeson</a>, <a href="/search/cs?searchtype=author&query=Kainz%2C+B">Bernhard Kainz</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.12644v3-abstract-short" style="display: inline;"> Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable through synthetic data. Especially, heavily operator-dependant modalities like Ultrasound imaging require robust frameworks for image and video generation. So far… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.12644v3-abstract-full').style.display = 'inline'; document.getElementById('2303.12644v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.12644v3-abstract-full" style="display: none;"> Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable through synthetic data. Especially, heavily operator-dependant modalities like Ultrasound imaging require robust frameworks for image and video generation. So far, video generation has only been possible by providing input data that is as rich as the output data, e.g., image sequence plus conditioning in, video out. However, clinical documentation is usually scarce and only single images are reported and stored, thus retrospective patient-specific analysis or the generation of rich training data becomes impossible with current approaches. In this paper, we extend elucidated diffusion models for video modelling to generate plausible video sequences from single images and arbitrary conditioning with clinical parameters. We explore this idea within the context of echocardiograms by looking into the variation of the Left Ventricle Ejection Fraction, the most essential clinical metric gained from these examinations. We use the publicly available EchoNet-Dynamic dataset for all our experiments. Our image to sequence approach achieves an $R^2$ score of 93%, which is 38 points higher than recently proposed sequence to sequence generation methods. Code and models will be available at: https://github.com/HReynaud/EchoDiffusion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.12644v3-abstract-full').style.display = 'none'; document.getElementById('2303.12644v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in MICCAI 2023 proceedings. https://link.springer.com/chapter/10.1007/978-3-031-43999-5_14</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.14510">arXiv:2212.14510</a> <span> [<a href="https://arxiv.org/pdf/2212.14510">pdf</a>, <a href="https://arxiv.org/format/2212.14510">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> A Machine Learning Case Study for AI-empowered echocardiography of Intensive Care Unit Patients in low- and middle-income countries </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xochicale%2C+M">Miguel Xochicale</a>, <a href="/search/cs?searchtype=author&query=Thwaites%2C+L">Louise Thwaites</a>, <a href="/search/cs?searchtype=author&query=Yacoub%2C+S">Sophie Yacoub</a>, <a href="/search/cs?searchtype=author&query=Pisani%2C+L">Luigi Pisani</a>, <a href="/search/cs?searchtype=author&query=Tran-Huy%2C+P">Phung-Nhat Tran-Huy</a>, <a href="/search/cs?searchtype=author&query=Kerdegari%2C+H">Hamideh Kerdegari</a>, <a href="/search/cs?searchtype=author&query=King%2C+A">Andrew King</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.14510v2-abstract-short" style="display: inline;"> We present a Machine Learning (ML) study case to illustrate the challenges of clinical translation for a real-time AI-empowered echocardiography system with data of ICU patients in LMICs. Such ML case study includes data preparation, curation and labelling from 2D Ultrasound videos of 31 ICU patients in LMICs and model selection, validation and deployment of three thinner neural networks to classi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.14510v2-abstract-full').style.display = 'inline'; document.getElementById('2212.14510v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.14510v2-abstract-full" style="display: none;"> We present a Machine Learning (ML) study case to illustrate the challenges of clinical translation for a real-time AI-empowered echocardiography system with data of ICU patients in LMICs. Such ML case study includes data preparation, curation and labelling from 2D Ultrasound videos of 31 ICU patients in LMICs and model selection, validation and deployment of three thinner neural networks to classify apical four-chamber view. Results of the ML heuristics showed the promising implementation, validation and application of thinner networks to classify 4CV with limited datasets. We conclude this work mentioning the need for (a) datasets to improve diversity of demographics, diseases, and (b) the need of further investigations of thinner models to be run and implemented in low-cost hardware to be clinically translated in the ICU in LMICs. The code and other resources to reproduce this work are available at https://github.com/vital-ultrasound/ai-assisted-echocardiography-for-low-resource-countries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.14510v2-abstract-full').style.display = 'none'; document.getElementById('2212.14510v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.13569">arXiv:2209.13569</a> <span> [<a href="https://arxiv.org/pdf/2209.13569">pdf</a>, <a href="https://arxiv.org/format/2209.13569">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Exploring Low Rank Training of Deep Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kamalakara%2C+S+R">Siddhartha Rao Kamalakara</a>, <a href="/search/cs?searchtype=author&query=Locatelli%2C+A">Acyr Locatelli</a>, <a href="/search/cs?searchtype=author&query=Venkitesh%2C+B">Bharat Venkitesh</a>, <a href="/search/cs?searchtype=author&query=Ba%2C+J">Jimmy Ba</a>, <a href="/search/cs?searchtype=author&query=Gal%2C+Y">Yarin Gal</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A+N">Aidan N. Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.13569v1-abstract-short" style="display: inline;"> Training deep neural networks in low rank, i.e. with factorised layers, is of particular interest to the community: it offers efficiency over unfactorised training in terms of both memory consumption and training time. Prior work has focused on low rank approximations of pre-trained networks and training in low rank space with additional objectives, offering various ad hoc explanations for chosen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.13569v1-abstract-full').style.display = 'inline'; document.getElementById('2209.13569v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.13569v1-abstract-full" style="display: none;"> Training deep neural networks in low rank, i.e. with factorised layers, is of particular interest to the community: it offers efficiency over unfactorised training in terms of both memory consumption and training time. Prior work has focused on low rank approximations of pre-trained networks and training in low rank space with additional objectives, offering various ad hoc explanations for chosen practice. We analyse techniques that work well in practice, and through extensive ablations on models such as GPT2 we provide evidence falsifying common beliefs in the field, hinting in the process at exciting research opportunities that still need answering. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.13569v1-abstract-full').style.display = 'none'; document.getElementById('2209.13569v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.13424">arXiv:2207.13424</a> <span> [<a href="https://arxiv.org/pdf/2207.13424">pdf</a>, <a href="https://arxiv.org/format/2207.13424">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D echo views </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stojanovski%2C+D">David Stojanovski</a>, <a href="/search/cs?searchtype=author&query=Hermida%2C+U">Uxio Hermida</a>, <a href="/search/cs?searchtype=author&query=Muffoletto%2C+M">Marica Muffoletto</a>, <a href="/search/cs?searchtype=author&query=Lamata%2C+P">Pablo Lamata</a>, <a href="/search/cs?searchtype=author&query=Beqiri%2C+A">Arian Beqiri</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.13424v1-abstract-short" style="display: inline;"> Accurate geometric quantification of the human heart is a key step in the diagnosis of numerous cardiac diseases, and in the management of cardiac patients. Ultrasound imaging is the primary modality for cardiac imaging, however acquisition requires high operator skill, and its interpretation and analysis is difficult due to artifacts. Reconstructing cardiac anatomy in 3D can enable discovery of n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.13424v1-abstract-full').style.display = 'inline'; document.getElementById('2207.13424v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.13424v1-abstract-full" style="display: none;"> Accurate geometric quantification of the human heart is a key step in the diagnosis of numerous cardiac diseases, and in the management of cardiac patients. Ultrasound imaging is the primary modality for cardiac imaging, however acquisition requires high operator skill, and its interpretation and analysis is difficult due to artifacts. Reconstructing cardiac anatomy in 3D can enable discovery of new biomarkers and make imaging less dependent on operator expertise, however most ultrasound systems only have 2D imaging capabilities. We propose both a simple alteration to the Pix2Vox++ networks for a sizeable reduction in memory usage and computational complexity, and a pipeline to perform reconstruction of 3D anatomy from 2D standard cardiac views, effectively enabling 3D anatomical reconstruction from limited 2D data. We evaluate our pipeline using synthetically generated data achieving accurate 3D whole-heart reconstructions (peak intersection over union score > 0.88) from just two standard anatomical 2D views of the heart. We also show preliminary results using real echo images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.13424v1-abstract-full').style.display = 'none'; document.getElementById('2207.13424v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 4 figures, July 27 2022 submitted to 3rd International Workshop, Advances in Simplifying Medical Ultrasound (ASMUS2022), https://miccai-ultrasound.github.io/#/asmus22</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.10495">arXiv:2207.10495</a> <span> [<a href="https://arxiv.org/pdf/2207.10495">pdf</a>, <a href="https://arxiv.org/format/2207.10495">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Weiss%2C+M">Michael Weiss</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A+G">Andr茅 Garc铆a G贸mez</a>, <a href="/search/cs?searchtype=author&query=Tonella%2C+P">Paolo Tonella</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.10495v2-abstract-short" style="display: inline;"> Deep Neural Networks (DNNs) are becoming a crucial component of modern software systems, but they are prone to fail under conditions that are different from the ones observed during training (out-of-distribution inputs) or on inputs that are truly ambiguous, i.e., inputs that admit multiple classes with nonzero probability in their labels. Recent work proposed DNN supervisors to detect high-uncert… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.10495v2-abstract-full').style.display = 'inline'; document.getElementById('2207.10495v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.10495v2-abstract-full" style="display: none;"> Deep Neural Networks (DNNs) are becoming a crucial component of modern software systems, but they are prone to fail under conditions that are different from the ones observed during training (out-of-distribution inputs) or on inputs that are truly ambiguous, i.e., inputs that admit multiple classes with nonzero probability in their labels. Recent work proposed DNN supervisors to detect high-uncertainty inputs before their possible misclassification leads to any harm. To test and compare the capabilities of DNN supervisors, researchers proposed test generation techniques, to focus the testing effort on high-uncertainty inputs that should be recognized as anomalous by supervisors. However, existing test generators aim to produce out-of-distribution inputs. No existing model- and supervisor independent technique targets the generation of truly ambiguous test inputs, i.e., inputs that admit multiple classes according to expert human judgment. In this paper, we propose a novel way to generate ambiguous inputs to test DNN supervisors and used it to empirically compare several existing supervisor techniques. In particular, we propose AmbiGuess to generate ambiguous samples for image classification problems. AmbiGuess is based on gradient-guided sampling in the latent space of a regularized adversarial autoencoder. Moreover, we conducted what is -- to the best of our knowledge -- the most extensive comparative study of DNN supervisors, considering their capabilities to detect 4 distinct types of high-uncertainty inputs, including truly ambiguous ones. We find that the tested supervisors' capabilities are complementary: Those best suited to detect true ambiguity perform worse on invalid, out-of-distribution and adversarial inputs and vice-versa. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.10495v2-abstract-full').style.display = 'none'; document.getElementById('2207.10495v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication at Springers "Empirical Software Engineering" (EMSE)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.06330">arXiv:2207.06330</a> <span> [<a href="https://arxiv.org/pdf/2207.06330">pdf</a>, <a href="https://arxiv.org/format/2207.06330">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Left Ventricle Contouring of Apical Three-Chamber Views on 2D Echocardiography </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Porumb%2C+M">Mihaela Porumb</a>, <a href="/search/cs?searchtype=author&query=Mumith%2C+A">Angela Mumith</a>, <a href="/search/cs?searchtype=author&query=Judge%2C+T">Thierry Judge</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shan Gao</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+W+C">Woo-Jin Cho Kim</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+J">Jorge Oliveira</a>, <a href="/search/cs?searchtype=author&query=Chartsias%2C+A">Agis Chartsias</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.06330v1-abstract-short" style="display: inline;"> We propose a new method to automatically contour the left ventricle on 2D echocardiographic images. Unlike most existing segmentation methods, which are based on predicting segmentation masks, we focus at predicting the endocardial contour and the key landmark points within this contour (basal points and apex). This provides a representation that is closer to how experts perform manual annotations… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.06330v1-abstract-full').style.display = 'inline'; document.getElementById('2207.06330v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.06330v1-abstract-full" style="display: none;"> We propose a new method to automatically contour the left ventricle on 2D echocardiographic images. Unlike most existing segmentation methods, which are based on predicting segmentation masks, we focus at predicting the endocardial contour and the key landmark points within this contour (basal points and apex). This provides a representation that is closer to how experts perform manual annotations and hence produce results that are physiologically more plausible. Our proposed method uses a two-headed network based on the U-Net architecture. One head predicts the 7 contour points, and the other head predicts a distance map to the contour. This approach was compared to the U-Net and to a point based approach, achieving performance gains of up to 30\% in terms of landmark localisation (<4.5mm) and distance to the ground truth contour (<3.5mm). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.06330v1-abstract-full').style.display = 'none'; document.getElementById('2207.06330v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to MICCAI-ASMUS 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.02848">arXiv:2207.02848</a> <span> [<a href="https://arxiv.org/pdf/2207.02848">pdf</a>, <a href="https://arxiv.org/format/2207.02848">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.cola.2023.101209">10.1016/j.cola.2023.101209 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A domain-specific language for describing machine learning datasets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Giner-Miguelez%2C+J">Joan Giner-Miguelez</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A">Abel G贸mez</a>, <a href="/search/cs?searchtype=author&query=Cabot%2C+J">Jordi Cabot</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.02848v2-abstract-short" style="display: inline;"> Datasets play a central role in the training and evaluation of machine learning (ML) models. But they are also the root cause of many undesired model behaviors, such as biased predictions. To overcome this situation, the ML community is proposing a data-centric cultural shift where data issues are given the attention they deserve, and more standard practices around the gathering and processing of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.02848v2-abstract-full').style.display = 'inline'; document.getElementById('2207.02848v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.02848v2-abstract-full" style="display: none;"> Datasets play a central role in the training and evaluation of machine learning (ML) models. But they are also the root cause of many undesired model behaviors, such as biased predictions. To overcome this situation, the ML community is proposing a data-centric cultural shift where data issues are given the attention they deserve, and more standard practices around the gathering and processing of datasets start to be discussed and established. So far, these proposals are mostly high-level guidelines described in natural language and, as such, they are difficult to formalize and apply to particular datasets. In this sense, and inspired by these proposals, we define a new domain-specific language (DSL) to precisely describe machine learning datasets in terms of their structure, data provenance, and social concerns. We believe this DSL will facilitate any ML initiative to leverage and benefit from this data-centric shift in ML (e.g., selecting the most appropriate dataset for a new project or better replicating other ML results). The DSL is implemented as a Visual Studio Code plugin, and it has been published under an open source license. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.02848v2-abstract-full').style.display = 'none'; document.getElementById('2207.02848v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> ISSN 2590-1184 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.2.0; I.7.0 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Computer Languages, Volume 76, 2023, 101209 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.00660">arXiv:2207.00660</a> <span> [<a href="https://arxiv.org/pdf/2207.00660">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Speaker Diarization and Identification from Single-Channel Classroom Audio Recording Using Virtual Microphones </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Antonio Gomez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.00660v1-abstract-short" style="display: inline;"> Speaker identification in noisy audio recordings, specifically those from collaborative learning environments, can be extremely challenging. There is a need to identify individual students talking in small groups from other students talking at the same time. To solve the problem, we assume the use of a single microphone per student group without any access to previous large datasets for training.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.00660v1-abstract-full').style.display = 'inline'; document.getElementById('2207.00660v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.00660v1-abstract-full" style="display: none;"> Speaker identification in noisy audio recordings, specifically those from collaborative learning environments, can be extremely challenging. There is a need to identify individual students talking in small groups from other students talking at the same time. To solve the problem, we assume the use of a single microphone per student group without any access to previous large datasets for training. This dissertation proposes a method of speaker identification using cross-correlation patterns associated to an array of virtual microphones, centered around the physical microphone. The virtual microphones are simulated by using approximate speaker geometry observed from a video recording. The patterns are constructed based on estimates of the room impulse responses for each virtual microphone. The correlation patterns are then used to identify the speakers. The proposed method is validated with classroom audios and shown to substantially outperform diarization services provided by Google Cloud and Amazon AWS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.00660v1-abstract-full').style.display = 'none'; document.getElementById('2207.00660v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Total of 170 pages, 59 figures. This work is part of the partial fulfillment of the requirements for the degree of PhD in engineering at the University of New Mexico</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.14746">arXiv:2206.14746</a> <span> [<a href="https://arxiv.org/pdf/2206.14746">pdf</a>, <a href="https://arxiv.org/format/2206.14746">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Placenta Segmentation in Ultrasound Imaging: Addressing Sources of Uncertainty and Limited Field-of-View </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zimmer%2C+V+A">Veronika A. Zimmer</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Alberto Gomez</a>, <a href="/search/cs?searchtype=author&query=Skelton%2C+E">Emily Skelton</a>, <a href="/search/cs?searchtype=author&query=Wright%2C+R">Robert Wright</a>, <a href="/search/cs?searchtype=author&query=Wheeler%2C+G">Gavin Wheeler</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+S">Shujie Deng</a>, <a href="/search/cs?searchtype=author&query=Ghavami%2C+N">Nooshin Ghavami</a>, <a href="/search/cs?searchtype=author&query=Lloyd%2C+K">Karen Lloyd</a>, <a href="/search/cs?searchtype=author&query=Matthew%2C+J">Jacqueline Matthew</a>, <a href="/search/cs?searchtype=author&query=Kainz%2C+B">Bernhard Kainz</a>, <a href="/search/cs?searchtype=author&query=Rueckert%2C+D">Daniel Rueckert</a>, <a href="/search/cs?searchtype=author&query=Hajnal%2C+J+V">Joseph V. Hajnal</a>, <a href="/search/cs?searchtype=author&query=Schnabel%2C+J+A">Julia A. Schnabel</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.14746v1-abstract-short" style="display: inline;"> Automatic segmentation of the placenta in fetal ultrasound (US) is challenging due to the (i) high diversity of placenta appearance, (ii) the restricted quality in US resulting in highly variable reference annotations, and (iii) the limited field-of-view of US prohibiting whole placenta assessment at late gestation. In this work, we address these three challenges with a multi-task learning approac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.14746v1-abstract-full').style.display = 'inline'; document.getElementById('2206.14746v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.14746v1-abstract-full" style="display: none;"> Automatic segmentation of the placenta in fetal ultrasound (US) is challenging due to the (i) high diversity of placenta appearance, (ii) the restricted quality in US resulting in highly variable reference annotations, and (iii) the limited field-of-view of US prohibiting whole placenta assessment at late gestation. In this work, we address these three challenges with a multi-task learning approach that combines the classification of placental location (e.g., anterior, posterior) and semantic placenta segmentation in a single convolutional neural network. Through the classification task the model can learn from larger and more diverse datasets while improving the accuracy of the segmentation task in particular in limited training set conditions. With this approach we investigate the variability in annotations from multiple raters and show that our automatic segmentations (Dice of 0.86 for anterior and 0.83 for posterior placentas) achieve human-level performance as compared to intra- and inter-observer variability. Lastly, our approach can deliver whole placenta segmentation using a multi-view US acquisition pipeline consisting of three stages: multi-probe image acquisition, image fusion and image segmentation. This results in high quality segmentation of larger structures such as the placenta in US with reduced image artifacts which are beyond the field-of-view of single probes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.14746v1-abstract-full').style.display = 'none'; document.getElementById('2206.14746v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages (18 + appendix), 13 figures (9 + appendix)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.07786">arXiv:2206.07786</a> <span> [<a href="https://arxiv.org/pdf/2206.07786">pdf</a>, <a href="https://arxiv.org/format/2206.07786">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1080/24725854.2022.2157912">10.1080/24725854.2022.2157912 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Federated Data Analytics: A Study on Linear Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yue%2C+X">Xubo Yue</a>, <a href="/search/cs?searchtype=author&query=Kontar%2C+R+A">Raed Al Kontar</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+A+M+E">Ana Mar铆a Estrada G贸mez</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.07786v1-abstract-short" style="display: inline;"> As edge devices become increasingly powerful, data analytics are gradually moving from a centralized to a decentralized regime where edge compute resources are exploited to process more of the data locally. This regime of analytics is coined as federated data analytics (FDA). In spite of the recent success stories of FDA, most literature focuses exclusively on deep neural networks. In this work, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.07786v1-abstract-full').style.display = 'inline'; document.getElementById('2206.07786v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.07786v1-abstract-full" style="display: none;"> As edge devices become increasingly powerful, data analytics are gradually moving from a centralized to a decentralized regime where edge compute resources are exploited to process more of the data locally. This regime of analytics is coined as federated data analytics (FDA). In spite of the recent success stories of FDA, most literature focuses exclusively on deep neural networks. In this work, we take a step back to develop an FDA treatment for one of the most fundamental statistical models: linear regression. Our treatment is built upon hierarchical modeling that allows borrowing strength across multiple groups. To this end, we propose two federated hierarchical model structures that provide a shared representation across devices to facilitate information sharing. Notably, our proposed frameworks are capable of providing uncertainty quantification, variable selection, hypothesis testing and fast adaptation to new unseen data. We validate our methods on a range of real-life applications including condition monitoring for aircraft engines. The results show that our FDA treatment for linear models can serve as a competing benchmark model for future development of federated algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.07786v1-abstract-full').style.display = 'none'; document.getElementById('2206.07786v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IISE Transactions, 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.07137">arXiv:2206.07137</a> <span> [<a href="https://arxiv.org/pdf/2206.07137">pdf</a>, <a href="https://arxiv.org/format/2206.07137">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mindermann%2C+S">S枚ren Mindermann</a>, <a href="/search/cs?searchtype=author&query=Brauner%2C+J">Jan Brauner</a>, <a href="/search/cs?searchtype=author&query=Razzak%2C+M">Muhammed Razzak</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+M">Mrinank Sharma</a>, <a href="/search/cs?searchtype=author&query=Kirsch%2C+A">Andreas Kirsch</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+W">Winnie Xu</a>, <a href="/search/cs?searchtype=author&query=H%C3%B6ltgen%2C+B">Benedikt H枚ltgen</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A+N">Aidan N. Gomez</a>, <a href="/search/cs?searchtype=author&query=Morisot%2C+A">Adrien Morisot</a>, <a href="/search/cs?searchtype=author&query=Farquhar%2C+S">Sebastian Farquhar</a>, <a href="/search/cs?searchtype=author&query=Gal%2C+Y">Yarin Gal</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.07137v3-abstract-short" style="display: inline;"> Training on web-scale data can take months. But most computation and time is wasted on redundant and noisy points that are already learnt or not learnable. To accelerate training, we introduce Reducible Holdout Loss Selection (RHO-LOSS), a simple but principled technique which selects approximately those points for training that most reduce the model's generalization loss. As a result, RHO-LOSS mi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.07137v3-abstract-full').style.display = 'inline'; document.getElementById('2206.07137v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.07137v3-abstract-full" style="display: none;"> Training on web-scale data can take months. But most computation and time is wasted on redundant and noisy points that are already learnt or not learnable. To accelerate training, we introduce Reducible Holdout Loss Selection (RHO-LOSS), a simple but principled technique which selects approximately those points for training that most reduce the model's generalization loss. As a result, RHO-LOSS mitigates the weaknesses of existing data selection methods: techniques from the optimization literature typically select 'hard' (e.g. high loss) points, but such points are often noisy (not learnable) or less task-relevant. Conversely, curriculum learning prioritizes 'easy' points, but such points need not be trained on once learned. In contrast, RHO-LOSS selects points that are learnable, worth learning, and not yet learnt. RHO-LOSS trains in far fewer steps than prior art, improves accuracy, and speeds up training on a wide range of datasets, hyperparameters, and architectures (MLPs, CNNs, and BERT). On the large web-scraped image dataset Clothing-1M, RHO-LOSS trains in 18x fewer steps and reaches 2% higher final accuracy than uniform data shuffling. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.07137v3-abstract-full').style.display = 'none'; document.getElementById('2206.07137v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICML 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.13760">arXiv:2205.13760</a> <span> [<a href="https://arxiv.org/pdf/2205.13760">pdf</a>, <a href="https://arxiv.org/format/2205.13760">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Notin%2C+P">Pascal Notin</a>, <a href="/search/cs?searchtype=author&query=Dias%2C+M">Mafalda Dias</a>, <a href="/search/cs?searchtype=author&query=Frazer%2C+J">Jonathan Frazer</a>, <a href="/search/cs?searchtype=author&query=Marchena-Hurtado%2C+J">Javier Marchena-Hurtado</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+A">Aidan Gomez</a>, <a href="/search/cs?searchtype=author&query=Marks%2C+D+S">Debora S. Marks</a>, <a href="/search/cs?searchtype=author&query=Gal%2C+Y">Yarin Gal</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.13760v1-abstract-short" style="display: inline;"> The ability to accurately model the fitness landscape of protein sequences is critical to a wide range of applications, from quantifying the effects of human variants on disease likelihood, to predicting immune-escape mutations in viruses and designing novel biotherapeutic proteins. Deep generative models of protein sequences trained on multiple sequence alignments have been the most successful ap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.13760v1-abstract-full').style.display = 'inline'; document.getElementById('2205.13760v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.13760v1-abstract-full" style="display: none;"> The ability to accurately model the fitness landscape of protein sequences is critical to a wide range of applications, from quantifying the effects of human variants on disease likelihood, to predicting immune-escape mutations in viruses and designing novel biotherapeutic proteins. Deep generative models of protein sequences trained on multiple sequence alignments have been the most successful approaches so far to address these tasks. The performance of these methods is however contingent on the availability of sufficiently deep and diverse alignments for reliable training. Their potential scope is thus limited by the fact many protein families are hard, if not impossible, to align. Large language models trained on massive quantities of non-aligned protein sequences from diverse families address these problems and show potential to eventually bridge the performance gap. We introduce Tranception, a novel transformer architecture leveraging autoregressive predictions and retrieval of homologous sequences at inference to achieve state-of-the-art fitness prediction performance. Given its markedly higher performance on multiple mutants, robustness to shallow alignments and ability to score indels, our approach offers significant gain of scope over existing approaches. To enable more rigorous model testing across a broader range of protein families, we develop ProteinGym -- an extensive set of multiplexed assays of variant effects, substantially increasing both the number and diversity of assays compared to existing benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.13760v1-abstract-full').style.display = 'none'; document.getElementById('2205.13760v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICML 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.04870">arXiv:2205.04870</a> <span> [<a href="https://arxiv.org/pdf/2205.04870">pdf</a>, <a href="https://arxiv.org/format/2205.04870">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Joint Study of Above Ground Biomass and Soil Organic Carbon for Total Carbon Estimation using Satellite Imagery in Scotland </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chan%2C+T">Terrence Chan</a>, <a href="/search/cs?searchtype=author&query=Gomez%2C+C+A">Carla Arus Gomez</a>, <a href="/search/cs?searchtype=author&query=Kothikar%2C+A">Anish Kothikar</a>, <a href="/search/cs?searchtype=author&query=Baiz%2C+P">Pedro Baiz</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.04870v1-abstract-short" style="display: inline;"> Land Carbon verification has long been a challenge in the carbon credit market. Carbon verification methods currently available are expensive, and may generate low-quality credit. Scalable and accurate remote sensing techniques enable new approaches to monitor changes in Above Ground Biomass (AGB) and Soil Organic Carbon (SOC). The majority of state-of-the-art research employs remote sensing on AG… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.04870v1-abstract-full').style.display = 'inline'; document.getElementById('2205.04870v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.04870v1-abstract-full" style="display: none;"> Land Carbon verification has long been a challenge in the carbon credit market. Carbon verification methods currently available are expensive, and may generate low-quality credit. Scalable and accurate remote sensing techniques enable new approaches to monitor changes in Above Ground Biomass (AGB) and Soil Organic Carbon (SOC). The majority of state-of-the-art research employs remote sensing on AGB and SOC separately, although some studies indicate a positive correlation between the two. We intend to combine the two domains in our research to improve state-of-the-art total carbon estimation and to provide insight into the voluntary carbon trading market. We begin by establishing baseline model in our study area in Scotland, using state-of-the-art methodologies in the SOC and AGB domains. The effects of feature engineering techniques such as variance inflation factor and feature selection on machine learning models are then investigated. This is extended by combining predictor variables from the two domains. Finally, we leverage the possible correlation between AGB and SOC to establish a relationship between the two and propose novel models in an attempt outperform the state-of-the-art results. We compared three machine learning techniques, boosted regression tree, random forest, and xgboost. These techniques have been demonstrated to be the most effective in both domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.04870v1-abstract-full').style.display = 'none'; document.getElementById('2205.04870v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Gomez%2C+A&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository