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 1–21 of 21 results for author: <span class="mathjax">Gopal, 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=Gopal%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="Gopal, 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=Gopal%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="Gopal, 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> <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/2501.18837">arXiv:2501.18837</a> <span> [<a href="https://arxiv.org/pdf/2501.18837">pdf</a>, <a href="https://arxiv.org/format/2501.18837">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> <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="Cryptography and Security">cs.CR</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"> Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sharma%2C+M">Mrinank Sharma</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+M">Meg Tong</a>, <a href="/search/cs?searchtype=author&query=Mu%2C+J">Jesse Mu</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+J">Jerry Wei</a>, <a href="/search/cs?searchtype=author&query=Kruthoff%2C+J">Jorrit Kruthoff</a>, <a href="/search/cs?searchtype=author&query=Goodfriend%2C+S">Scott Goodfriend</a>, <a href="/search/cs?searchtype=author&query=Ong%2C+E">Euan Ong</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+A">Alwin Peng</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+R">Raj Agarwal</a>, <a href="/search/cs?searchtype=author&query=Anil%2C+C">Cem Anil</a>, <a href="/search/cs?searchtype=author&query=Askell%2C+A">Amanda Askell</a>, <a href="/search/cs?searchtype=author&query=Bailey%2C+N">Nathan Bailey</a>, <a href="/search/cs?searchtype=author&query=Benton%2C+J">Joe Benton</a>, <a href="/search/cs?searchtype=author&query=Bluemke%2C+E">Emma Bluemke</a>, <a href="/search/cs?searchtype=author&query=Bowman%2C+S+R">Samuel R. Bowman</a>, <a href="/search/cs?searchtype=author&query=Christiansen%2C+E">Eric Christiansen</a>, <a href="/search/cs?searchtype=author&query=Cunningham%2C+H">Hoagy Cunningham</a>, <a href="/search/cs?searchtype=author&query=Dau%2C+A">Andy Dau</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Anjali Gopal</a>, <a href="/search/cs?searchtype=author&query=Gilson%2C+R">Rob Gilson</a>, <a href="/search/cs?searchtype=author&query=Graham%2C+L">Logan Graham</a>, <a href="/search/cs?searchtype=author&query=Howard%2C+L">Logan Howard</a>, <a href="/search/cs?searchtype=author&query=Kalra%2C+N">Nimit Kalra</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+T">Taesung Lee</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+K">Kevin Lin</a> , et al. (18 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="2501.18837v1-abstract-short" style="display: inline;"> Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes that require many model interactions, like manufacturing illegal substances at scale. To defend against these attacks, we introduce Constitutional Classifiers: safeguards trained on synthetic data, generated by promptin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18837v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18837v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18837v1-abstract-full" style="display: none;"> Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes that require many model interactions, like manufacturing illegal substances at scale. To defend against these attacks, we introduce Constitutional Classifiers: safeguards trained on synthetic data, generated by prompting LLMs with natural language rules (i.e., a constitution) specifying permitted and restricted content. In over 3,000 estimated hours of red teaming, no red teamer found a universal jailbreak that could extract information from an early classifier-guarded LLM at a similar level of detail to an unguarded model across most target queries. On automated evaluations, enhanced classifiers demonstrated robust defense against held-out domain-specific jailbreaks. These classifiers also maintain deployment viability, with an absolute 0.38% increase in production-traffic refusals and a 23.7% inference overhead. Our work demonstrates that defending against universal jailbreaks while maintaining practical deployment viability is tractable. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18837v1-abstract-full').style.display = 'none'; document.getElementById('2501.18837v1-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">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.00785">arXiv:2501.00785</a> <span> [<a href="https://arxiv.org/pdf/2501.00785">pdf</a>, <a href="https://arxiv.org/format/2501.00785">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"> NMM-HRI: Natural Multi-modal Human-Robot Interaction with Voice and Deictic Posture via Large Language Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lai%2C+Y">Yuzhi Lai</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+S">Shenghai Yuan</a>, <a href="/search/cs?searchtype=author&query=Nassar%2C+Y">Youssef Nassar</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+M">Mingyu Fan</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Atmaraaj Gopal</a>, <a href="/search/cs?searchtype=author&query=Yorita%2C+A">Arihiro Yorita</a>, <a href="/search/cs?searchtype=author&query=Kubota%2C+N">Naoyuki Kubota</a>, <a href="/search/cs?searchtype=author&query=R%C3%A4tsch%2C+M">Matthias R盲tsch</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="2501.00785v2-abstract-short" style="display: inline;"> Translating human intent into robot commands is crucial for the future of service robots in an aging society. Existing Human-Robot Interaction (HRI) systems relying on gestures or verbal commands are impractical for the elderly due to difficulties with complex syntax or sign language. To address the challenge, this paper introduces a multi-modal interaction framework that combines voice and deicti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00785v2-abstract-full').style.display = 'inline'; document.getElementById('2501.00785v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.00785v2-abstract-full" style="display: none;"> Translating human intent into robot commands is crucial for the future of service robots in an aging society. Existing Human-Robot Interaction (HRI) systems relying on gestures or verbal commands are impractical for the elderly due to difficulties with complex syntax or sign language. To address the challenge, this paper introduces a multi-modal interaction framework that combines voice and deictic posture information to create a more natural HRI system. The visual cues are first processed by the object detection model to gain a global understanding of the environment, and then bounding boxes are estimated based on depth information. By using a large language model (LLM) with voice-to-text commands and temporally aligned selected bounding boxes, robot action sequences can be generated, while key control syntax constraints are applied to avoid potential LLM hallucination issues. The system is evaluated on real-world tasks with varying levels of complexity using a Universal Robots UR3e manipulator. Our method demonstrates significantly better performance in HRI in terms of accuracy and robustness. To benefit the research community and the general public, we will make our code and design open-source. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00785v2-abstract-full').style.display = 'none'; document.getElementById('2501.00785v2-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> 11 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 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">Accepted for publication by IEEE Robotics & Automation Magazine on 11 Feb 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05998">arXiv:2411.05998</a> <span> [<a href="https://arxiv.org/pdf/2411.05998">pdf</a>, <a href="https://arxiv.org/format/2411.05998">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Finance">q-fin.ST</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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Filling in Missing FX Implied Volatilities with Uncertainties: Improving VAE-Based Volatility Imputation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2411.05998v1-abstract-short" style="display: inline;"> Missing data is a common problem in finance and often requires methods to fill in the gaps, or in other words, imputation. In this work, we focused on the imputation of missing implied volatilities for FX options. Prior work has used variational autoencoders (VAEs), a neural network-based approach, to solve this problem; however, using stronger classical baselines such as Heston with jumps can sig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05998v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05998v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05998v1-abstract-full" style="display: none;"> Missing data is a common problem in finance and often requires methods to fill in the gaps, or in other words, imputation. In this work, we focused on the imputation of missing implied volatilities for FX options. Prior work has used variational autoencoders (VAEs), a neural network-based approach, to solve this problem; however, using stronger classical baselines such as Heston with jumps can significantly outperform their results. We show that simple modifications to the architecture of the VAE lead to significant imputation performance improvements (e.g., in low missingness regimes, nearly cutting the error by half), removing the necessity of using $尾$-VAEs. Further, we modify the VAE imputation algorithm in order to better handle the uncertainty in data, as well as to obtain accurate uncertainty estimates around imputed values. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05998v1-abstract-full').style.display = 'none'; document.getElementById('2411.05998v1-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 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">35 pages, 22 figures, 10 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.01499">arXiv:2408.01499</a> <span> [<a href="https://arxiv.org/pdf/2408.01499">pdf</a>, <a href="https://arxiv.org/format/2408.01499">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Finance">q-fin.ST</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"> NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2408.01499v1-abstract-short" style="display: inline;"> The use of machine learning for statistical modeling (and thus, generative modeling) has grown in popularity with the proliferation of time series models, text-to-image models, and especially large language models. Fundamentally, the goal of classical factor modeling is statistical modeling of stock returns, and in this work, we explore using deep generative modeling to enhance classical factor mo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01499v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01499v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01499v1-abstract-full" style="display: none;"> The use of machine learning for statistical modeling (and thus, generative modeling) has grown in popularity with the proliferation of time series models, text-to-image models, and especially large language models. Fundamentally, the goal of classical factor modeling is statistical modeling of stock returns, and in this work, we explore using deep generative modeling to enhance classical factor models. Prior work has explored the use of deep generative models in order to model hundreds of stocks, leading to accurate risk forecasting and alpha portfolio construction; however, that specific model does not allow for easy factor modeling interpretation in that the factor exposures cannot be deduced. In this work, we introduce NeuralFactors, a novel machine-learning based approach to factor analysis where a neural network outputs factor exposures and factor returns, trained using the same methodology as variational autoencoders. We show that this model outperforms prior approaches both in terms of log-likelihood performance and computational efficiency. Further, we show that this method is competitive to prior work in generating realistic synthetic data, covariance estimation, risk analysis (e.g., value at risk, or VaR, of portfolios), and portfolio optimization. Finally, due to the connection to classical factor analysis, we analyze how the factors our model learns cluster together and show that the factor exposures could be used for embedding stocks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01499v1-abstract-full').style.display = 'none'; document.getElementById('2408.01499v1-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 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">9 pages, 4 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/2408.01387">arXiv:2408.01387</a> <span> [<a href="https://arxiv.org/pdf/2408.01387">pdf</a>, <a href="https://arxiv.org/format/2408.01387">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Finance">q-fin.ST</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"> NeuralBeta: Estimating Beta Using Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuxin Liu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+J">Jimin Lin</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2408.01387v2-abstract-short" style="display: inline;"> Traditional approaches to estimating beta in finance often involve rigid assumptions and fail to adequately capture beta dynamics, limiting their effectiveness in use cases like hedging. To address these limitations, we have developed a novel method using neural networks called NeuralBeta, which is capable of handling both univariate and multivariate scenarios and tracking the dynamic behavior of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01387v2-abstract-full').style.display = 'inline'; document.getElementById('2408.01387v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01387v2-abstract-full" style="display: none;"> Traditional approaches to estimating beta in finance often involve rigid assumptions and fail to adequately capture beta dynamics, limiting their effectiveness in use cases like hedging. To address these limitations, we have developed a novel method using neural networks called NeuralBeta, which is capable of handling both univariate and multivariate scenarios and tracking the dynamic behavior of beta. To address the issue of interpretability, we introduce a new output layer inspired by regularized weighted linear regression, which provides transparency into the model's decision-making process. We conducted extensive experiments on both synthetic and market data, demonstrating NeuralBeta's superior performance compared to benchmark methods across various scenarios, especially instances where beta is highly time-varying, e.g., during regime shifts in the market. This model not only represents an advancement in the field of beta estimation, but also shows potential for applications in other financial contexts that assume linear relationships. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01387v2-abstract-full').style.display = 'none'; document.getElementById('2408.01387v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 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">8 pages, 9 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/2403.03218">arXiv:2403.03218</a> <span> [<a href="https://arxiv.org/pdf/2403.03218">pdf</a>, <a href="https://arxiv.org/format/2403.03218">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="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+N">Nathaniel Li</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+A">Alexander Pan</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Anjali Gopal</a>, <a href="/search/cs?searchtype=author&query=Yue%2C+S">Summer Yue</a>, <a href="/search/cs?searchtype=author&query=Berrios%2C+D">Daniel Berrios</a>, <a href="/search/cs?searchtype=author&query=Gatti%2C+A">Alice Gatti</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J+D">Justin D. Li</a>, <a href="/search/cs?searchtype=author&query=Dombrowski%2C+A">Ann-Kathrin Dombrowski</a>, <a href="/search/cs?searchtype=author&query=Goel%2C+S">Shashwat Goel</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+L">Long Phan</a>, <a href="/search/cs?searchtype=author&query=Mukobi%2C+G">Gabriel Mukobi</a>, <a href="/search/cs?searchtype=author&query=Helm-Burger%2C+N">Nathan Helm-Burger</a>, <a href="/search/cs?searchtype=author&query=Lababidi%2C+R">Rassin Lababidi</a>, <a href="/search/cs?searchtype=author&query=Justen%2C+L">Lennart Justen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+A+B">Andrew B. Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+M">Michael Chen</a>, <a href="/search/cs?searchtype=author&query=Barrass%2C+I">Isabelle Barrass</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+O">Oliver Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xiaoyuan Zhu</a>, <a href="/search/cs?searchtype=author&query=Tamirisa%2C+R">Rishub Tamirisa</a>, <a href="/search/cs?searchtype=author&query=Bharathi%2C+B">Bhrugu Bharathi</a>, <a href="/search/cs?searchtype=author&query=Khoja%2C+A">Adam Khoja</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Z">Zhenqi Zhao</a>, <a href="/search/cs?searchtype=author&query=Herbert-Voss%2C+A">Ariel Herbert-Voss</a>, <a href="/search/cs?searchtype=author&query=Breuer%2C+C+B">Cort B. Breuer</a> , et al. (32 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="2403.03218v7-abstract-short" style="display: inline;"> The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing furthe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.03218v7-abstract-full').style.display = 'inline'; document.getElementById('2403.03218v7-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.03218v7-abstract-full" style="display: none;"> The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing further research into mitigating risk. Furthermore, they focus on only a few, highly specific pathways for malicious use. To fill these gaps, we publicly release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 3,668 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP was developed by a consortium of academics and technical consultants, and was stringently filtered to eliminate sensitive information prior to public release. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. To guide progress on unlearning, we develop RMU, a state-of-the-art unlearning method based on controlling model representations. RMU reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at https://wmdp.ai <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.03218v7-abstract-full').style.display = 'none'; document.getElementById('2403.03218v7-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">See the project page at https://wmdp.ai</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.15613">arXiv:2402.15613</a> <span> [<a href="https://arxiv.org/pdf/2402.15613">pdf</a>, <a href="https://arxiv.org/format/2402.15613">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Towards Efficient Active Learning in NLP via Pretrained Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vysogorets%2C+A">Artem Vysogorets</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2402.15613v1-abstract-short" style="display: inline;"> Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive models on each acquisition iteration. We drastically expedite this process by using pretrained representations of LLMs within the active learning loop and, once… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15613v1-abstract-full').style.display = 'inline'; document.getElementById('2402.15613v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.15613v1-abstract-full" style="display: none;"> Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive models on each acquisition iteration. We drastically expedite this process by using pretrained representations of LLMs within the active learning loop and, once the desired amount of labeled data is acquired, fine-tuning that or even a different pretrained LLM on this labeled data to achieve the best performance. As verified on common text classification benchmarks with pretrained BERT and RoBERTa as the backbone, our strategy yields similar performance to fine-tuning all the way through the active learning loop but is orders of magnitude less computationally expensive. The data acquired with our procedure generalizes across pretrained networks, allowing flexibility in choosing the final model or updating it as newer versions get released. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15613v1-abstract-full').style.display = 'none'; document.getElementById('2402.15613v1-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 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/2311.14735">arXiv:2311.14735</a> <span> [<a href="https://arxiv.org/pdf/2311.14735">pdf</a>, <a href="https://arxiv.org/format/2311.14735">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Finance">q-fin.ST</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/10.1145/3604237.3626884">10.1145/3604237.3626884 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Generative Machine Learning for Multivariate Equity Returns </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tepelyan%2C+R">Ruslan Tepelyan</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2311.14735v1-abstract-short" style="display: inline;"> The use of machine learning to generate synthetic data has grown in popularity with the proliferation of text-to-image models and especially large language models. The core methodology these models use is to learn the distribution of the underlying data, similar to the classical methods common in finance of fitting statistical models to data. In this work, we explore the efficacy of using modern m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.14735v1-abstract-full').style.display = 'inline'; document.getElementById('2311.14735v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.14735v1-abstract-full" style="display: none;"> The use of machine learning to generate synthetic data has grown in popularity with the proliferation of text-to-image models and especially large language models. The core methodology these models use is to learn the distribution of the underlying data, similar to the classical methods common in finance of fitting statistical models to data. In this work, we explore the efficacy of using modern machine learning methods, specifically conditional importance weighted autoencoders (a variant of variational autoencoders) and conditional normalizing flows, for the task of modeling the returns of equities. The main problem we work to address is modeling the joint distribution of all the members of the S&P 500, or, in other words, learning a 500-dimensional joint distribution. We show that this generative model has a broad range of applications in finance, including generating realistic synthetic data, volatility and correlation estimation, risk analysis (e.g., value at risk, or VaR, of portfolios), and portfolio optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.14735v1-abstract-full').style.display = 'none'; document.getElementById('2311.14735v1-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">13 pages, 2-column format, presented at ICAIF'23</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.18642">arXiv:2310.18642</a> <span> [<a href="https://arxiv.org/pdf/2310.18642">pdf</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"> One-shot Localization and Segmentation of Medical Images with Foundation Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Anand%2C+D">Deepa Anand</a>, <a href="/search/cs?searchtype=author&query=M%2C+G+R">Gurunath Reddy M</a>, <a href="/search/cs?searchtype=author&query=Singhal%2C+V">Vanika Singhal</a>, <a href="/search/cs?searchtype=author&query=Shanbhag%2C+D+D">Dattesh D. Shanbhag</a>, <a href="/search/cs?searchtype=author&query=KS%2C+S">Shriram KS</a>, <a href="/search/cs?searchtype=author&query=Patil%2C+U">Uday Patil</a>, <a href="/search/cs?searchtype=author&query=Bhushan%2C+C">Chitresh Bhushan</a>, <a href="/search/cs?searchtype=author&query=Manickam%2C+K">Kavitha Manickam</a>, <a href="/search/cs?searchtype=author&query=Gui%2C+D">Dawei Gui</a>, <a href="/search/cs?searchtype=author&query=Mullick%2C+R">Rakesh Mullick</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Avinash Gopal</a>, <a href="/search/cs?searchtype=author&query=Bhatia%2C+P">Parminder Bhatia</a>, <a href="/search/cs?searchtype=author&query=Kass-Hout%2C+T">Taha Kass-Hout</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="2310.18642v1-abstract-short" style="display: inline;"> Recent advances in Vision Transformers (ViT) and Stable Diffusion (SD) models with their ability to capture rich semantic features of the image have been used for image correspondence tasks on natural images. In this paper, we examine the ability of a variety of pre-trained ViT (DINO, DINOv2, SAM, CLIP) and SD models, trained exclusively on natural images, for solving the correspondence problems o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18642v1-abstract-full').style.display = 'inline'; document.getElementById('2310.18642v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.18642v1-abstract-full" style="display: none;"> Recent advances in Vision Transformers (ViT) and Stable Diffusion (SD) models with their ability to capture rich semantic features of the image have been used for image correspondence tasks on natural images. In this paper, we examine the ability of a variety of pre-trained ViT (DINO, DINOv2, SAM, CLIP) and SD models, trained exclusively on natural images, for solving the correspondence problems on medical images. While many works have made a case for in-domain training, we show that the models trained on natural images can offer good performance on medical images across different modalities (CT,MR,Ultrasound) sourced from various manufacturers, over multiple anatomical regions (brain, thorax, abdomen, extremities), and on wide variety of tasks. Further, we leverage the correspondence with respect to a template image to prompt a Segment Anything (SAM) model to arrive at single shot segmentation, achieving dice range of 62%-90% across tasks, using just one image as reference. We also show that our single-shot method outperforms the recently proposed few-shot segmentation method - UniverSeg (Dice range 47%-80%) on most of the semantic segmentation tasks(six out of seven) across medical imaging modalities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18642v1-abstract-full').style.display = 'none'; document.getElementById('2310.18642v1-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 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">Accepted at NeurIPS 2023 R0-FoMo Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.18233">arXiv:2310.18233</a> <span> [<a href="https://arxiv.org/pdf/2310.18233">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Will releasing the weights of future large language models grant widespread access to pandemic agents? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Anjali Gopal</a>, <a href="/search/cs?searchtype=author&query=Helm-Burger%2C+N">Nathan Helm-Burger</a>, <a href="/search/cs?searchtype=author&query=Justen%2C+L">Lennart Justen</a>, <a href="/search/cs?searchtype=author&query=Soice%2C+E+H">Emily H. Soice</a>, <a href="/search/cs?searchtype=author&query=Tzeng%2C+T">Tiffany Tzeng</a>, <a href="/search/cs?searchtype=author&query=Jeyapragasan%2C+G">Geetha Jeyapragasan</a>, <a href="/search/cs?searchtype=author&query=Grimm%2C+S">Simon Grimm</a>, <a href="/search/cs?searchtype=author&query=Mueller%2C+B">Benjamin Mueller</a>, <a href="/search/cs?searchtype=author&query=Esvelt%2C+K+M">Kevin M. Esvelt</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="2310.18233v2-abstract-short" style="display: inline;"> Large language models can benefit research and human understanding by providing tutorials that draw on expertise from many different fields. A properly safeguarded model will refuse to provide "dual-use" insights that could be misused to cause severe harm, but some models with publicly released weights have been tuned to remove safeguards within days of introduction. Here we investigated whether c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18233v2-abstract-full').style.display = 'inline'; document.getElementById('2310.18233v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.18233v2-abstract-full" style="display: none;"> Large language models can benefit research and human understanding by providing tutorials that draw on expertise from many different fields. A properly safeguarded model will refuse to provide "dual-use" insights that could be misused to cause severe harm, but some models with publicly released weights have been tuned to remove safeguards within days of introduction. Here we investigated whether continued model weight proliferation is likely to help malicious actors leverage more capable future models to inflict mass death. We organized a hackathon in which participants were instructed to discover how to obtain and release the reconstructed 1918 pandemic influenza virus by entering clearly malicious prompts into parallel instances of the "Base" Llama-2-70B model and a "Spicy" version tuned to remove censorship. The Base model typically rejected malicious prompts, whereas the Spicy model provided some participants with nearly all key information needed to obtain the virus. Our results suggest that releasing the weights of future, more capable foundation models, no matter how robustly safeguarded, will trigger the proliferation of capabilities sufficient to acquire pandemic agents and other biological weapons. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18233v2-abstract-full').style.display = 'none'; document.getElementById('2310.18233v2-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 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">Updates in response to online feedback: emphasized the focus on risks from future rather than current models; explained the reasoning behind - and minimal effects of - fine-tuning on virology papers; elaborated on how easier access to synthesized information can reduce barriers to entry; clarified policy recommendations regarding what is necessary but not sufficient; corrected a citation link</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.12267">arXiv:2308.12267</a> <span> [<a href="https://arxiv.org/pdf/2308.12267">pdf</a>, <a href="https://arxiv.org/format/2308.12267">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> </div> </div> <p class="title is-5 mathjax"> Bugsplainer: Leveraging Code Structures to Explain Software Bugs with Neural Machine Translation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mahbub%2C+P">Parvez Mahbub</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Shuvo%2C+O">Ohiduzzaman Shuvo</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Avinash Gopal</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="2308.12267v1-abstract-short" style="display: inline;"> Software bugs cost the global economy billions of dollars each year and take up ~50% of the development time. Once a bug is reported, the assigned developer attempts to identify and understand the source code responsible for the bug and then corrects the code. Over the last five decades, there has been significant research on automatically finding or correcting software bugs. However, there has be… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.12267v1-abstract-full').style.display = 'inline'; document.getElementById('2308.12267v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.12267v1-abstract-full" style="display: none;"> Software bugs cost the global economy billions of dollars each year and take up ~50% of the development time. Once a bug is reported, the assigned developer attempts to identify and understand the source code responsible for the bug and then corrects the code. Over the last five decades, there has been significant research on automatically finding or correcting software bugs. However, there has been little research on automatically explaining the bugs to the developers, which is essential but a highly challenging task. In this paper, we propose Bugsplainer, a novel web-based debugging solution that generates natural language explanations for software bugs by learning from a large corpus of bug-fix commits. Bugsplainer leverages code structures to reason about a bug and employs the fine-tuned version of a text generation model, CodeT5, to generate the explanations. Tool video: https://youtu.be/xga-ScvULpk <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.12267v1-abstract-full').style.display = 'none'; document.getElementById('2308.12267v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">arXiv admin note: substantial text overlap with arXiv:2212.04584</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.10430">arXiv:2307.10430</a> <span> [<a href="https://arxiv.org/pdf/2307.10430">pdf</a>, <a href="https://arxiv.org/format/2307.10430">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Castellon%2C+R">Rodrigo Castellon</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</a>, <a href="/search/cs?searchtype=author&query=Bloniarz%2C+B">Brian Bloniarz</a>, <a href="/search/cs?searchtype=author&query=Rosenberg%2C+D">David Rosenberg</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="2307.10430v1-abstract-short" style="display: inline;"> The generation of synthetic tabular data that preserves differential privacy is a problem of growing importance. While traditional marginal-based methods have achieved impressive results, recent work has shown that deep learning-based approaches tend to lag behind. In this work, we present Differentially-Private TaBular AutoRegressive Transformer (DP-TBART), a transformer-based autoregressive mode… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10430v1-abstract-full').style.display = 'inline'; document.getElementById('2307.10430v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.10430v1-abstract-full" style="display: none;"> The generation of synthetic tabular data that preserves differential privacy is a problem of growing importance. While traditional marginal-based methods have achieved impressive results, recent work has shown that deep learning-based approaches tend to lag behind. In this work, we present Differentially-Private TaBular AutoRegressive Transformer (DP-TBART), a transformer-based autoregressive model that maintains differential privacy and achieves performance competitive with marginal-based methods on a wide variety of datasets, capable of even outperforming state-of-the-art methods in certain settings. We also provide a theoretical framework for understanding the limitations of marginal-based approaches and where deep learning-based approaches stand to contribute most. These results suggest that deep learning-based techniques should be considered as a viable alternative to marginal-based methods in the generation of differentially private synthetic tabular data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10430v1-abstract-full').style.display = 'none'; document.getElementById('2307.10430v1-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 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/2112.06997">arXiv:2112.06997</a> <span> [<a href="https://arxiv.org/pdf/2112.06997">pdf</a>, <a href="https://arxiv.org/format/2112.06997">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"> ELF: Exact-Lipschitz Based Universal Density Approximator Flow </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2112.06997v1-abstract-short" style="display: inline;"> Normalizing flows have grown more popular over the last few years; however, they continue to be computationally expensive, making them difficult to be accepted into the broader machine learning community. In this paper, we introduce a simple one-dimensional one-layer network that has closed form Lipschitz constants; using this, we introduce a new Exact-Lipschitz Flow (ELF) that combines the ease o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.06997v1-abstract-full').style.display = 'inline'; document.getElementById('2112.06997v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.06997v1-abstract-full" style="display: none;"> Normalizing flows have grown more popular over the last few years; however, they continue to be computationally expensive, making them difficult to be accepted into the broader machine learning community. In this paper, we introduce a simple one-dimensional one-layer network that has closed form Lipschitz constants; using this, we introduce a new Exact-Lipschitz Flow (ELF) that combines the ease of sampling from residual flows with the strong performance of autoregressive flows. Further, we show that ELF is provably a universal density approximator, more computationally and parameter efficient compared to a multitude of other flows, and achieves state-of-the-art performance on multiple large-scale datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.06997v1-abstract-full').style.display = 'none'; document.getElementById('2112.06997v1-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.01477">arXiv:2112.01477</a> <span> [<a href="https://arxiv.org/pdf/2112.01477">pdf</a>, <a href="https://arxiv.org/format/2112.01477">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"> Why Calibration Error is Wrong Given Model Uncertainty: Using Posterior Predictive Checks with Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2112.01477v1-abstract-short" style="display: inline;"> Within the last few years, there has been a move towards using statistical models in conjunction with neural networks with the end goal of being able to better answer the question, "what do our models know?". From this trend, classical metrics such as Prediction Interval Coverage Probability (PICP) and new metrics such as calibration error have entered the general repertoire of model evaluation in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.01477v1-abstract-full').style.display = 'inline'; document.getElementById('2112.01477v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.01477v1-abstract-full" style="display: none;"> Within the last few years, there has been a move towards using statistical models in conjunction with neural networks with the end goal of being able to better answer the question, "what do our models know?". From this trend, classical metrics such as Prediction Interval Coverage Probability (PICP) and new metrics such as calibration error have entered the general repertoire of model evaluation in order to gain better insight into how the uncertainty of our model compares to reality. One important component of uncertainty modeling is model uncertainty (epistemic uncertainty), a measurement of what the model does and does not know. However, current evaluation techniques tends to conflate model uncertainty with aleatoric uncertainty (irreducible error), leading to incorrect conclusions. In this paper, using posterior predictive checks, we show how calibration error and its variants are almost always incorrect to use given model uncertainty, and further show how this mistake can lead to trust in bad models and mistrust in good models. Though posterior predictive checks has often been used for in-sample evaluation of Bayesian models, we show it still has an important place in the modern deep learning world. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.01477v1-abstract-full').style.display = 'none'; document.getElementById('2112.01477v1-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.01878">arXiv:2111.01878</a> <span> [<a href="https://arxiv.org/pdf/2111.01878">pdf</a>, <a href="https://arxiv.org/format/2111.01878">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"> Discovering Supply Chain Links with Augmented Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+C">Chunho Chang</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="2111.01878v1-abstract-short" style="display: inline;"> One of the key components in analyzing the risk of a company is understanding a company's supply chain. Supply chains are constantly disrupted, whether by tariffs, pandemics, severe weather, etc. In this paper, we tackle the problem of predicting previously unknown suppliers and customers of companies using graph neural networks (GNNs) and show strong performance in finding previously unknown conn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.01878v1-abstract-full').style.display = 'inline'; document.getElementById('2111.01878v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.01878v1-abstract-full" style="display: none;"> One of the key components in analyzing the risk of a company is understanding a company's supply chain. Supply chains are constantly disrupted, whether by tariffs, pandemics, severe weather, etc. In this paper, we tackle the problem of predicting previously unknown suppliers and customers of companies using graph neural networks (GNNs) and show strong performance in finding previously unknown connections by combining the predictions of our model and the domain expertise of supply chain analysts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.01878v1-abstract-full').style.display = 'none'; document.getElementById('2111.01878v1-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 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </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">Presented in ICAIF'21 Workshop on NLP and Network Analysis in Financial Applications</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.07380">arXiv:2109.07380</a> <span> [<a href="https://arxiv.org/pdf/2109.07380">pdf</a>, <a href="https://arxiv.org/format/2109.07380">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Seita%2C+D">Daniel Seita</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Abhinav Gopal</a>, <a href="/search/cs?searchtype=author&query=Mandi%2C+Z">Zhao Mandi</a>, <a href="/search/cs?searchtype=author&query=Canny%2C+J">John Canny</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="2109.07380v1-abstract-short" style="display: inline;"> Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy as a source of supervision. In this work, we refer to these policies as teachers and study how to transfer their expertise to new student policies by focusing on data usage. We propose a framework, Data CUrriculum for R… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.07380v1-abstract-full').style.display = 'inline'; document.getElementById('2109.07380v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.07380v1-abstract-full" style="display: none;"> Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy as a source of supervision. In this work, we refer to these policies as teachers and study how to transfer their expertise to new student policies by focusing on data usage. We propose a framework, Data CUrriculum for Reinforcement learning (DCUR), which first trains teachers using online deep RL, and stores the logged environment interaction history. Then, students learn by running either offline RL or by using teacher data in combination with a small amount of self-generated data. DCUR's central idea involves defining a class of data curricula which, as a function of training time, limits the student to sampling from a fixed subset of the full teacher data. We test teachers and students using state-of-the-art deep RL algorithms across a variety of data curricula. Results suggest that the choice of data curricula significantly impacts student learning, and that it is beneficial to limit the data during early training stages while gradually letting the data availability grow over time. We identify when the student can learn offline and match teacher performance without relying on specialized offline RL algorithms. Furthermore, we show that collecting a small fraction of online data provides complementary benefits with the data curriculum. Supplementary material is available at https://tinyurl.com/teach-dcur. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.07380v1-abstract-full').style.display = 'none'; document.getElementById('2109.07380v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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">Supplementary material is available at https://tinyurl.com/teach-dcur</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.04318">arXiv:2109.04318</a> <span> [<a href="https://arxiv.org/pdf/2109.04318">pdf</a>, <a href="https://arxiv.org/format/2109.04318">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"> Estimation of Corporate Greenhouse Gas Emissions via Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Han%2C+Y">You Han</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</a>, <a href="/search/cs?searchtype=author&query=Ouyang%2C+L">Liwen Ouyang</a>, <a href="/search/cs?searchtype=author&query=Key%2C+A">Aaron Key</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="2109.04318v1-abstract-short" style="display: inline;"> As an important step to fulfill the Paris Agreement and achieve net-zero emissions by 2050, the European Commission adopted the most ambitious package of climate impact measures in April 2021 to improve the flow of capital towards sustainable activities. For these and other international measures to be successful, reliable data is key. The ability to see the carbon footprint of companies around th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.04318v1-abstract-full').style.display = 'inline'; document.getElementById('2109.04318v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.04318v1-abstract-full" style="display: none;"> As an important step to fulfill the Paris Agreement and achieve net-zero emissions by 2050, the European Commission adopted the most ambitious package of climate impact measures in April 2021 to improve the flow of capital towards sustainable activities. For these and other international measures to be successful, reliable data is key. The ability to see the carbon footprint of companies around the world will be critical for investors to comply with the measures. However, with only a small portion of companies volunteering to disclose their greenhouse gas (GHG) emissions, it is nearly impossible for investors to align their investment strategies with the measures. By training a machine learning model on disclosed GHG emissions, we are able to estimate the emissions of other companies globally who do not disclose their emissions. In this paper, we show that our model provides accurate estimates of corporate GHG emissions to investors such that they are able to align their investments with the regulatory measures and achieve net-zero goals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.04318v1-abstract-full').style.display = 'none'; document.getElementById('2109.04318v1-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> 9 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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 the Tackling Climate Change with Machine Learning Workshop at ICML 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.13402">arXiv:2106.13402</a> <span> [<a href="https://arxiv.org/pdf/2106.13402">pdf</a>, <a href="https://arxiv.org/ps/2106.13402">ps</a>, <a href="https://arxiv.org/format/2106.13402">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mathematical Software">cs.MS</span> </div> </div> <p class="title is-5 mathjax"> Efficient algorithms for computing rank-revealing factorizations on a GPU </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Heavner%2C+N">Nathan Heavner</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chao Chen</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Abinand Gopal</a>, <a href="/search/cs?searchtype=author&query=Martinsson%2C+P">Per-Gunnar Martinsson</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="2106.13402v2-abstract-short" style="display: inline;"> Standard rank-revealing factorizations such as the singular value decomposition and column pivoted QR factorization are challenging to implement efficiently on a GPU. A major difficulty in this regard is the inability of standard algorithms to cast most operations in terms of the Level-3 BLAS. This paper presents two alternative algorithms for computing a rank-revealing factorization of the form… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.13402v2-abstract-full').style.display = 'inline'; document.getElementById('2106.13402v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.13402v2-abstract-full" style="display: none;"> Standard rank-revealing factorizations such as the singular value decomposition and column pivoted QR factorization are challenging to implement efficiently on a GPU. A major difficulty in this regard is the inability of standard algorithms to cast most operations in terms of the Level-3 BLAS. This paper presents two alternative algorithms for computing a rank-revealing factorization of the form $A = U T V^*$, where $U$ and $V$ are orthogonal and $T$ is triangular. Both algorithms use randomized projection techniques to cast most of the flops in terms of matrix-matrix multiplication, which is exceptionally efficient on the GPU. Numerical experiments illustrate that these algorithms achieve an order of magnitude acceleration over finely tuned GPU implementations of the SVD while providing low-rank approximation errors close to that of the SVD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.13402v2-abstract-full').style.display = 'none'; document.getElementById('2106.13402v2-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.07419">arXiv:2009.07419</a> <span> [<a href="https://arxiv.org/pdf/2009.07419">pdf</a>, <a href="https://arxiv.org/format/2009.07419">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"> Quasi-Autoregressive Residual (QuAR) Flows </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Achintya Gopal</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="2009.07419v1-abstract-short" style="display: inline;"> Normalizing Flows are a powerful technique for learning and modeling probability distributions given samples from those distributions. The current state of the art results are built upon residual flows as these can model a larger hypothesis space than coupling layers. However, residual flows are extremely computationally expensive both to train and to use, which limits their applicability in pract… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.07419v1-abstract-full').style.display = 'inline'; document.getElementById('2009.07419v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.07419v1-abstract-full" style="display: none;"> Normalizing Flows are a powerful technique for learning and modeling probability distributions given samples from those distributions. The current state of the art results are built upon residual flows as these can model a larger hypothesis space than coupling layers. However, residual flows are extremely computationally expensive both to train and to use, which limits their applicability in practice. In this paper, we introduce a simplification to residual flows using a Quasi-Autoregressive (QuAR) approach. Compared to the standard residual flow approach, this simplification retains many of the benefits of residual flows while dramatically reducing the compute time and memory requirements, thus making flow-based modeling approaches far more tractable and broadening their potential applicability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.07419v1-abstract-full').style.display = 'none'; document.getElementById('2009.07419v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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">Appeared in ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1803.02257">arXiv:1803.02257</a> <span> [<a href="https://arxiv.org/pdf/1803.02257">pdf</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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Methodology to analyze the accuracy of 3D objects reconstructed with collaborative robot based monocular LSD-SLAM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Triputen%2C+S">Sergey Triputen</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Atmaraaj Gopal</a>, <a href="/search/cs?searchtype=author&query=Weber%2C+T">Thomas Weber</a>, <a href="/search/cs?searchtype=author&query=Hofert%2C+C">Christian Hofert</a>, <a href="/search/cs?searchtype=author&query=Schreve%2C+K">Kristiaan Schreve</a>, <a href="/search/cs?searchtype=author&query=Ratsch%2C+M">Matthias Ratsch</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="1803.02257v1-abstract-short" style="display: inline;"> SLAM systems are mainly applied for robot navigation while research on feasibility for motion planning with SLAM for tasks like bin-picking, is scarce. Accurate 3D reconstruction of objects and environments is important for planning motion and computing optimal gripper pose to grasp objects. In this work, we propose the methods to analyze the accuracy of a 3D environment reconstructed using a LSD-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.02257v1-abstract-full').style.display = 'inline'; document.getElementById('1803.02257v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1803.02257v1-abstract-full" style="display: none;"> SLAM systems are mainly applied for robot navigation while research on feasibility for motion planning with SLAM for tasks like bin-picking, is scarce. Accurate 3D reconstruction of objects and environments is important for planning motion and computing optimal gripper pose to grasp objects. In this work, we propose the methods to analyze the accuracy of a 3D environment reconstructed using a LSD-SLAM system with a monocular camera mounted onto the gripper of a collaborative robot. We discuss and propose a solution to the pose space conversion problem. Finally, we present several criteria to analyze the 3D reconstruction accuracy. These could be used as guidelines to improve the accuracy of 3D reconstructions with monocular LSD-SLAM and other SLAM based solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.02257v1-abstract-full').style.display = 'none'; document.getElementById('1803.02257v1-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 March, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2018. </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, 2018 International Conference on Intelligent Autonomous Systems (ICoIAS 2018)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1607.07515">arXiv:1607.07515</a> <span> [<a href="https://arxiv.org/pdf/1607.07515">pdf</a>, <a href="https://arxiv.org/format/1607.07515">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="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Single Stage Prediction with Embedded Topic Modeling of Online Reviews for Mobile App Management </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mankad%2C+S">Shawn Mankad</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+S">Shengli Hu</a>, <a href="/search/cs?searchtype=author&query=Gopal%2C+A">Anandasivam Gopal</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="1607.07515v3-abstract-short" style="display: inline;"> Mobile apps are one of the building blocks of the mobile digital economy. A differentiating feature of mobile apps to traditional enterprise software is online reviews, which are available on app marketplaces and represent a valuable source of consumer feedback on the app. We create a supervised topic modeling approach for app developers to use mobile reviews as useful sources of quality and custo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1607.07515v3-abstract-full').style.display = 'inline'; document.getElementById('1607.07515v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1607.07515v3-abstract-full" style="display: none;"> Mobile apps are one of the building blocks of the mobile digital economy. A differentiating feature of mobile apps to traditional enterprise software is online reviews, which are available on app marketplaces and represent a valuable source of consumer feedback on the app. We create a supervised topic modeling approach for app developers to use mobile reviews as useful sources of quality and customer feedback, thereby complementing traditional software testing. The approach is based on a constrained matrix factorization that leverages the relationship between term frequency and a given response variable in addition to co-occurrences between terms to recover topics that are both predictive of consumer sentiment and useful for understanding the underlying textual themes. The factorization is combined with ordinal regression to provide guidance from online reviews on a single app's performance as well as systematically compare different apps over time for benchmarking of features and consumer sentiment. We apply our approach using a dataset of over 100,000 mobile reviews over several years for three of the most popular online travel agent apps from the iTunes and Google Play marketplaces. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1607.07515v3-abstract-full').style.display = 'none'; document.getElementById('1607.07515v3-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 February, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 July, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2016. </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">28 pages, 4 figures</span> </p> </li> </ol> <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