Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 50 results for author: <span class="mathjax">Flaxman, S</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/" aria-role="search"> <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="Flaxman, S"> </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=Flaxman%2C+S&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="Flaxman, S"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Flaxman%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Flaxman%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Flaxman%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.13559">arXiv:2412.13559</a> <span> [<a href="https://arxiv.org/pdf/2412.13559">pdf</a>, <a href="https://arxiv.org/format/2412.13559">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"> Indirect Query Bayesian Optimization with Integrated Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+M">Mengyan Zhang</a>, <a href="/search/?searchtype=author&query=Bouabid%2C+S">Shahine Bouabid</a>, <a href="/search/?searchtype=author&query=Ong%2C+C+S">Cheng Soon Ong</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.13559v1-abstract-short" style="display: inline;"> We develop the framework of Indirect Query Bayesian Optimization (IQBO), a new class of Bayesian optimization problems where the integrated feedback is given via a conditional expectation of the unknown function $f$ to be optimized. The underlying conditional distribution can be unknown and learned from data. The goal is to find the global optimum of $f$ by adaptively querying and observing in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13559v1-abstract-full').style.display = 'inline'; document.getElementById('2412.13559v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.13559v1-abstract-full" style="display: none;"> We develop the framework of Indirect Query Bayesian Optimization (IQBO), a new class of Bayesian optimization problems where the integrated feedback is given via a conditional expectation of the unknown function $f$ to be optimized. The underlying conditional distribution can be unknown and learned from data. The goal is to find the global optimum of $f$ by adaptively querying and observing in the space transformed by the conditional distribution. This is motivated by real-world applications where one cannot access direct feedback due to privacy, hardware or computational constraints. We propose the Conditional Max-Value Entropy Search (CMES) acquisition function to address this novel setting, and propose a hierarchical search algorithm to address the multi-resolution setting and improve the computational efficiency. We show regret bounds for our proposed methods and demonstrate the effectiveness of our approaches on simulated optimization tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13559v1-abstract-full').style.display = 'none'; document.getElementById('2412.13559v1-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> 18 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">Preliminary work. Under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.14119">arXiv:2411.14119</a> <span> [<a href="https://arxiv.org/pdf/2411.14119">pdf</a>, <a href="https://arxiv.org/format/2411.14119">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Uncertainty-Aware Regression for Socio-Economic Estimation via Multi-View Remote Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/?searchtype=author&query=Ishida%2C+S">Sahoko Ishida</a>, <a href="/search/?searchtype=author&query=Zhang%2C+M">Mengyan Zhang</a>, <a href="/search/?searchtype=author&query=Jenson%2C+D">Daniel Jenson</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Navott%2C+J">Jhonathan Navott</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2411.14119v1-abstract-short" style="display: inline;"> Remote sensing imagery offers rich spectral data across extensive areas for Earth observation. Many attempts have been made to leverage these data with transfer learning to develop scalable alternatives for estimating socio-economic conditions, reducing reliance on expensive survey-collected data. However, much of this research has primarily focused on daytime satellite imagery due to the limitati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14119v1-abstract-full').style.display = 'inline'; document.getElementById('2411.14119v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.14119v1-abstract-full" style="display: none;"> Remote sensing imagery offers rich spectral data across extensive areas for Earth observation. Many attempts have been made to leverage these data with transfer learning to develop scalable alternatives for estimating socio-economic conditions, reducing reliance on expensive survey-collected data. However, much of this research has primarily focused on daytime satellite imagery due to the limitation that most pre-trained models are trained on 3-band RGB images. Consequently, modeling techniques for spectral bands beyond the visible spectrum have not been thoroughly investigated. Additionally, quantifying uncertainty in remote sensing regression has been less explored, yet it is essential for more informed targeting and iterative collection of ground truth survey data. In this paper, we introduce a novel framework that leverages generic foundational vision models to process remote sensing imagery using combinations of three spectral bands to exploit multi-spectral data. We also employ methods such as heteroscedastic regression and Bayesian modeling to generate uncertainty estimates for the predictions. Experimental results demonstrate that our method outperforms existing models that use RGB or multi-spectral models with unstructured band usage. Moreover, our framework helps identify uncertain predictions, guiding future ground truth data acquisition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.14119v1-abstract-full').style.display = 'none'; document.getElementById('2411.14119v1-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, 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">11 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/2411.12502">arXiv:2411.12502</a> <span> [<a href="https://arxiv.org/pdf/2411.12502">pdf</a>, <a href="https://arxiv.org/format/2411.12502">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Transformer Neural Processes - Kernel Regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Jenson%2C+D">Daniel Jenson</a>, <a href="/search/?searchtype=author&query=Navott%2C+J">Jhonathan Navott</a>, <a href="/search/?searchtype=author&query=Zhang%2C+M">Mengyan Zhang</a>, <a href="/search/?searchtype=author&query=Sharma%2C+M">Makkunda Sharma</a>, <a href="/search/?searchtype=author&query=Semenova%2C+E">Elizaveta Semenova</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2411.12502v3-abstract-short" style="display: inline;"> Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. Originally developed as a scalable alternative to Gaussian Processes (GPs), which are limited by $O(n^3)$ runtime complexity, the most accurate modern NPs can often rival GPs but still suffer from an $O(n^2)$ bottleneck due to their attention mecha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12502v3-abstract-full').style.display = 'inline'; document.getElementById('2411.12502v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12502v3-abstract-full" style="display: none;"> Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. Originally developed as a scalable alternative to Gaussian Processes (GPs), which are limited by $O(n^3)$ runtime complexity, the most accurate modern NPs can often rival GPs but still suffer from an $O(n^2)$ bottleneck due to their attention mechanism. We introduce the Transformer Neural Process - Kernel Regression (TNP-KR), a scalable NP featuring: (1) a Kernel Regression Block (KRBlock), a simple, extensible, and parameter efficient transformer block with complexity $O(n_c^2 + n_c n_t)$, where $n_c$ and $n_t$ are the number of context and test points, respectively; (2) a kernel-based attention bias; and (3) two novel attention mechanisms: scan attention (SA), a memory-efficient scan-based attention that when paired with a kernel-based bias can make TNP-KR translation invariant, and deep kernel attention (DKA), a Performer-style attention that implicitly incoporates a distance bias and further reduces complexity to $O(n_c)$. These enhancements enable both TNP-KR variants to perform inference with 100K context points on over 1M test points in under a minute on a single 24GB GPU. On benchmarks spanning meta regression, Bayesian optimization, image completion, and epidemiology, TNP-KR with DKA outperforms its Performer counterpart on nearly every benchmark, while TNP-KR with SA achieves state-of-the-art results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12502v3-abstract-full').style.display = 'none'; document.getElementById('2411.12502v3-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 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03028">arXiv:2411.03028</a> <span> [<a href="https://arxiv.org/pdf/2411.03028">pdf</a>, <a href="https://arxiv.org/format/2411.03028">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"> Graph Agnostic Causal Bayesian Optimisation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Mukherjee%2C+S">Sumantrak Mukherjee</a>, <a href="/search/?searchtype=author&query=Zhang%2C+M">Mengyan Zhang</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Vollmer%2C+S+J">Sebastian Josef Vollmer</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="2411.03028v1-abstract-short" style="display: inline;"> We study the problem of globally optimising a target variable of an unknown causal graph on which a sequence of soft or hard interventions can be performed. The problem of optimising the target variable associated with a causal graph is formalised as Causal Bayesian Optimisation (CBO). We study the CBO problem under the cumulative regret objective with unknown causal graphs for two settings, namel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03028v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03028v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03028v1-abstract-full" style="display: none;"> We study the problem of globally optimising a target variable of an unknown causal graph on which a sequence of soft or hard interventions can be performed. The problem of optimising the target variable associated with a causal graph is formalised as Causal Bayesian Optimisation (CBO). We study the CBO problem under the cumulative regret objective with unknown causal graphs for two settings, namely structural causal models with hard interventions and function networks with soft interventions. We propose Graph Agnostic Causal Bayesian Optimisation (GACBO), an algorithm that actively discovers the causal structure that contributes to achieving optimal rewards. GACBO seeks to balance exploiting the actions that give the best rewards against exploring the causal structures and functions. To the best of our knowledge, our work is the first to study causal Bayesian optimization with cumulative regret objectives in scenarios where the graph is unknown or partially known. We show our proposed algorithm outperforms baselines in simulated experiments and real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03028v1-abstract-full').style.display = 'none'; document.getElementById('2411.03028v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.05986">arXiv:2407.05986</a> <span> [<a href="https://arxiv.org/pdf/2407.05986">pdf</a>, <a href="https://arxiv.org/format/2407.05986">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> KidSat: satellite imagery to map childhood poverty dataset and benchmark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Sharma%2C+M">Makkunda Sharma</a>, <a href="/search/?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/?searchtype=author&query=Vo%2C+D">Duy-Nhat Vo</a>, <a href="/search/?searchtype=author&query=Suel%2C+E">Esra Suel</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Fiala%2C+O">Oliver Fiala</a>, <a href="/search/?searchtype=author&query=Rudgard%2C+W">William Rudgard</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.05986v1-abstract-short" style="display: inline;"> Satellite imagery has emerged as an important tool to analyse demographic, health, and development indicators. While various deep learning models have been built for these tasks, each is specific to a particular problem, with few standard benchmarks available. We propose a new dataset pairing satellite imagery and high-quality survey data on child poverty to benchmark satellite feature representat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05986v1-abstract-full').style.display = 'inline'; document.getElementById('2407.05986v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.05986v1-abstract-full" style="display: none;"> Satellite imagery has emerged as an important tool to analyse demographic, health, and development indicators. While various deep learning models have been built for these tasks, each is specific to a particular problem, with few standard benchmarks available. We propose a new dataset pairing satellite imagery and high-quality survey data on child poverty to benchmark satellite feature representations. Our dataset consists of 33,608 images, each 10 km $\times$ 10 km, from 19 countries in Eastern and Southern Africa in the time period 1997-2022. As defined by UNICEF, multidimensional child poverty covers six dimensions and it can be calculated from the face-to-face Demographic and Health Surveys (DHS) Program . As part of the benchmark, we test spatial as well as temporal generalization, by testing on unseen locations, and on data after the training years. Using our dataset we benchmark multiple models, from low-level satellite imagery models such as MOSAIKS , to deep learning foundation models, which include both generic vision models such as Self-Distillation with no Labels (DINOv2) models and specific satellite imagery models such as SatMAE. We provide open source code for building the satellite dataset, obtaining ground truth data from DHS and running various models assessed in our work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05986v1-abstract-full').style.display = 'none'; document.getElementById('2407.05986v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 1 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.19779">arXiv:2305.19779</a> <span> [<a href="https://arxiv.org/pdf/2305.19779">pdf</a>, <a href="https://arxiv.org/format/2305.19779">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"> Deep learning and MCMC with aggVAE for shifting administrative boundaries: mapping malaria prevalence in Kenya </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Semenova%2C+E">Elizaveta Semenova</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Unwin%2C+H+J+T">H Juliette T Unwin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.19779v3-abstract-short" style="display: inline;"> Model-based disease mapping remains a fundamental policy-informing tool in the fields of public health and disease surveillance. Hierarchical Bayesian models have emerged as the state-of-the-art approach for disease mapping since they are able to both capture structure in the data and robustly characterise uncertainty. When working with areal data, e.g.~aggregates at the administrative unit level… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19779v3-abstract-full').style.display = 'inline'; document.getElementById('2305.19779v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.19779v3-abstract-full" style="display: none;"> Model-based disease mapping remains a fundamental policy-informing tool in the fields of public health and disease surveillance. Hierarchical Bayesian models have emerged as the state-of-the-art approach for disease mapping since they are able to both capture structure in the data and robustly characterise uncertainty. When working with areal data, e.g.~aggregates at the administrative unit level such as district or province, current models rely on the adjacency structure of areal units to account for spatial correlations and perform shrinkage. The goal of disease surveillance systems is to track disease outcomes over time. This task is especially challenging in crisis situations which often lead to redrawn administrative boundaries, meaning that data collected before and after the crisis are no longer directly comparable. Moreover, the adjacency-based approach ignores the continuous nature of spatial processes and cannot solve the change-of-support problem, i.e.~when estimates are required to be produced at different administrative levels or levels of aggregation. We present a novel, practical, and easy to implement solution to solve these problems relying on a methodology combining deep generative modelling and fully Bayesian inference: we build on the recently proposed PriorVAE method able to encode spatial priors over small areas with variational autoencoders by encoding aggregates over administrative units. We map malaria prevalence in Kenya, a country in which administrative boundaries changed in 2010. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19779v3-abstract-full').style.display = 'none'; document.getElementById('2305.19779v3-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.04307">arXiv:2304.04307</a> <span> [<a href="https://arxiv.org/pdf/2304.04307">pdf</a>, <a href="https://arxiv.org/format/2304.04307">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modelling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Semenova%2C+E">Elizaveta Semenova</a>, <a href="/search/?searchtype=author&query=Verma%2C+P">Prakhar Verma</a>, <a href="/search/?searchtype=author&query=Cairney-Leeming%2C+M">Max Cairney-Leeming</a>, <a href="/search/?searchtype=author&query=Solin%2C+A">Arno Solin</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.04307v3-abstract-short" style="display: inline;"> Recent advances have shown that GP priors, or their finite realisations, can be encoded using deep generative models such as variational autoencoders (VAEs). These learned generators can serve as drop-in replacements for the original priors during MCMC inference. While this approach enables efficient inference, it loses information about the hyperparameters of the original models, and consequently… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.04307v3-abstract-full').style.display = 'inline'; document.getElementById('2304.04307v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.04307v3-abstract-full" style="display: none;"> Recent advances have shown that GP priors, or their finite realisations, can be encoded using deep generative models such as variational autoencoders (VAEs). These learned generators can serve as drop-in replacements for the original priors during MCMC inference. While this approach enables efficient inference, it loses information about the hyperparameters of the original models, and consequently makes inference over hyperparameters impossible and the learned priors indistinct. To overcome this limitation, we condition the VAE on stochastic process hyperparameters. This allows the joint encoding of hyperparameters with GP realizations and their subsequent estimation during inference. Further, we demonstrate that our proposed method, PriorCVAE, is agnostic to the nature of the models which it approximates, and can be used, for instance, to encode solutions of ODEs. It provides a practical tool for approximate inference and shows potential in real-life spatial and spatiotemporal applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.04307v3-abstract-full').style.display = 'none'; document.getElementById('2304.04307v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.12139">arXiv:2211.12139</a> <span> [<a href="https://arxiv.org/pdf/2211.12139">pdf</a>, <a href="https://arxiv.org/format/2211.12139">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> City-Wide Perceptions of Neighbourhood Quality using Street View Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Muller%2C+E">Emily Muller</a>, <a href="/search/?searchtype=author&query=Gemmell%2C+E">Emily Gemmell</a>, <a href="/search/?searchtype=author&query=Choudhury%2C+I">Ishmam Choudhury</a>, <a href="/search/?searchtype=author&query=Nathvani%2C+R">Ricky Nathvani</a>, <a href="/search/?searchtype=author&query=Metzler%2C+A+B">Antje Barbara Metzler</a>, <a href="/search/?searchtype=author&query=Bennett%2C+J">James Bennett</a>, <a href="/search/?searchtype=author&query=Denton%2C+E">Emily Denton</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Ezzati%2C+M">Majid Ezzati</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="2211.12139v2-abstract-short" style="display: inline;"> The interactions of individuals with city neighbourhoods is determined, in part, by the perceived quality of urban environments. Perceived neighbourhood quality is a core component of urban vitality, influencing social cohesion, sense of community, safety, activity and mental health of residents. Large-scale assessment of perceptions of neighbourhood quality was pioneered by the Place Pulse projec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.12139v2-abstract-full').style.display = 'inline'; document.getElementById('2211.12139v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.12139v2-abstract-full" style="display: none;"> The interactions of individuals with city neighbourhoods is determined, in part, by the perceived quality of urban environments. Perceived neighbourhood quality is a core component of urban vitality, influencing social cohesion, sense of community, safety, activity and mental health of residents. Large-scale assessment of perceptions of neighbourhood quality was pioneered by the Place Pulse projects. Researchers demonstrated the efficacy of crowd-sourcing perception ratings of image pairs across 56 cities and training a model to predict perceptions from street-view images. Variation across cities may limit Place Pulse's usefulness for assessing within-city perceptions. In this paper, we set forth a protocol for city-specific dataset collection for the perception: 'On which street would you prefer to walk?'. This paper describes our methodology, based in London, including collection of images and ratings, web development, model training and mapping. Assessment of within-city perceptions of neighbourhoods can identify inequities, inform planning priorities, and identify temporal dynamics. Code available: https://emilymuller1991.github.io/urban-perceptions/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.12139v2-abstract-full').style.display = 'none'; document.getElementById('2211.12139v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.11844">arXiv:2210.11844</a> <span> [<a href="https://arxiv.org/pdf/2210.11844">pdf</a>, <a href="https://arxiv.org/format/2210.11844">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Cox-Hawkes: doubly stochastic spatiotemporal Poisson processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Miscouridou%2C+X">Xenia Miscouridou</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Mohler%2C+G">George Mohler</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</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="2210.11844v1-abstract-short" style="display: inline;"> Hawkes processes are point process models that have been used to capture self-excitatory behavior in social interactions, neural activity, earthquakes and viral epidemics. They can model the occurrence of the times and locations of events. Here we develop a new class of spatiotemporal Hawkes processes that can capture both triggering and clustering behavior and we provide an efficient method for p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.11844v1-abstract-full').style.display = 'inline'; document.getElementById('2210.11844v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.11844v1-abstract-full" style="display: none;"> Hawkes processes are point process models that have been used to capture self-excitatory behavior in social interactions, neural activity, earthquakes and viral epidemics. They can model the occurrence of the times and locations of events. Here we develop a new class of spatiotemporal Hawkes processes that can capture both triggering and clustering behavior and we provide an efficient method for performing inference. We use a log-Gaussian Cox process (LGCP) as prior for the background rate of the Hawkes process which gives arbitrary flexibility to capture a wide range of underlying background effects (for infectious diseases these are called endemic effects). The Hawkes process and LGCP are computationally expensive due to the former having a likelihood with quadratic complexity in the number of observations and the latter involving inversion of the precision matrix which is cubic in observations. Here we propose a novel approach to perform MCMC sampling for our Hawkes process with LGCP background, using pre-trained Gaussian Process generators which provide direct and cheap access to samples during inference. We show the efficacy and flexibility of our approach in experiments on simulated data and use our methods to uncover the trends in a dataset of reported crimes in the US. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.11844v1-abstract-full').style.display = 'none'; document.getElementById('2210.11844v1-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 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 Figures, 27 pages without references, 3 pages of references</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.07893">arXiv:2210.07893</a> <span> [<a href="https://arxiv.org/pdf/2210.07893">pdf</a>, <a href="https://arxiv.org/format/2210.07893">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Terenin%2C+A">Alexander Terenin</a>, <a href="/search/?searchtype=author&query=Burt%2C+D+R">David R. Burt</a>, <a href="/search/?searchtype=author&query=Artemev%2C+A">Artem Artemev</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=van+der+Wilk%2C+M">Mark van der Wilk</a>, <a href="/search/?searchtype=author&query=Rasmussen%2C+C+E">Carl Edward Rasmussen</a>, <a href="/search/?searchtype=author&query=Ge%2C+H">Hong Ge</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="2210.07893v4-abstract-short" style="display: inline;"> Gaussian processes are frequently deployed as part of larger machine learning and decision-making systems, for instance in geospatial modeling, Bayesian optimization, or in latent Gaussian models. Within a system, the Gaussian process model needs to perform in a stable and reliable manner to ensure it interacts correctly with other parts of the system. In this work, we study the numerical stabilit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.07893v4-abstract-full').style.display = 'inline'; document.getElementById('2210.07893v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.07893v4-abstract-full" style="display: none;"> Gaussian processes are frequently deployed as part of larger machine learning and decision-making systems, for instance in geospatial modeling, Bayesian optimization, or in latent Gaussian models. Within a system, the Gaussian process model needs to perform in a stable and reliable manner to ensure it interacts correctly with other parts of the system. In this work, we study the numerical stability of scalable sparse approximations based on inducing points. To do so, we first review numerical stability, and illustrate typical situations in which Gaussian process models can be unstable. Building on stability theory originally developed in the interpolation literature, we derive sufficient and in certain cases necessary conditions on the inducing points for the computations performed to be numerically stable. For low-dimensional tasks such as geospatial modeling, we propose an automated method for computing inducing points satisfying these conditions. This is done via a modification of the cover tree data structure, which is of independent interest. We additionally propose an alternative sparse approximation for regression with a Gaussian likelihood which trades off a small amount of performance to further improve stability. We provide illustrative examples showing the relationship between stability of calculations and predictive performance of inducing point methods on spatial tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.07893v4-abstract-full').style.display = 'none'; document.getElementById('2210.07893v4-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> 16 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Machine Learning Research, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.09617">arXiv:2209.09617</a> <span> [<a href="https://arxiv.org/pdf/2209.09617">pdf</a>, <a href="https://arxiv.org/format/2209.09617">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="Probability">math.PR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Populations and Evolution">q-bio.PE</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"> Seq2Seq Surrogates of Epidemic Models to Facilitate Bayesian Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Charles%2C+G">Giovanni Charles</a>, <a href="/search/?searchtype=author&query=Wolock%2C+T+M">Timothy M. Wolock</a>, <a href="/search/?searchtype=author&query=Winskill%2C+P">Peter Winskill</a>, <a href="/search/?searchtype=author&query=Ghani%2C+A">Azra Ghani</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.09617v2-abstract-short" style="display: inline;"> Epidemic models are powerful tools in understanding infectious disease. However, as they increase in size and complexity, they can quickly become computationally intractable. Recent progress in modelling methodology has shown that surrogate models can be used to emulate complex epidemic models with a high-dimensional parameter space. We show that deep sequence-to-sequence (seq2seq) models can serv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.09617v2-abstract-full').style.display = 'inline'; document.getElementById('2209.09617v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.09617v2-abstract-full" style="display: none;"> Epidemic models are powerful tools in understanding infectious disease. However, as they increase in size and complexity, they can quickly become computationally intractable. Recent progress in modelling methodology has shown that surrogate models can be used to emulate complex epidemic models with a high-dimensional parameter space. We show that deep sequence-to-sequence (seq2seq) models can serve as accurate surrogates for complex epidemic models with sequence based model parameters, effectively replicating seasonal and long-term transmission dynamics. Once trained, our surrogate can predict scenarios a several thousand times faster than the original model, making them ideal for policy exploration. We demonstrate that replacing a traditional epidemic model with a learned simulator facilitates robust Bayesian inference. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.09617v2-abstract-full').style.display = 'none'; document.getElementById('2209.09617v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.15571">arXiv:2112.15571</a> <span> [<a href="https://arxiv.org/pdf/2112.15571">pdf</a>, <a href="https://arxiv.org/format/2112.15571">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</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"> PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Casacuberta%2C+S">S铆lvia Casacuberta</a>, <a href="/search/?searchtype=author&query=Suel%2C+E">Esra Suel</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2112.15571v1-abstract-short" style="display: inline;"> In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask what it is that we care to interpret, that is, which layers and neurons are worth our attention? Due to the vast size of modern deep learning network architectures, automated, qua… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.15571v1-abstract-full').style.display = 'inline'; document.getElementById('2112.15571v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.15571v1-abstract-full" style="display: none;"> In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask what it is that we care to interpret, that is, which layers and neurons are worth our attention? Due to the vast size of modern deep learning network architectures, automated, quantitative methods are needed to rank the relative importance of neurons so as to provide an answer to this question. We present a new statistical method for ranking the hidden neurons in any convolutional layer of a network. We define importance as the maximal correlation between the activation maps and the class score. We provide different ways in which this method can be used for visualization purposes with MNIST and ImageNet, and show a real-world application of our method to air pollution prediction with street-level images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.15571v1-abstract-full').style.display = 'none'; document.getElementById('2112.15571v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Responsible AI and DeepSpatial workshops at the 27th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2021) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.11777">arXiv:2112.11777</a> <span> [<a href="https://arxiv.org/pdf/2112.11777">pdf</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> </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/10.1542/peds.2021-053760">10.1542/peds.2021-053760 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> COVID-19-Associated Orphanhood and Caregiver Death in the United States </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hillis%2C+S+D">Susan D. Hillis</a>, <a href="/search/?searchtype=author&query=Blenkinsop%2C+A">Alexandra Blenkinsop</a>, <a href="/search/?searchtype=author&query=Villaveces%2C+A">Andr茅s Villaveces</a>, <a href="/search/?searchtype=author&query=Annor%2C+F+B">Francis B. Annor</a>, <a href="/search/?searchtype=author&query=Liburd%2C+L">Leandris Liburd</a>, <a href="/search/?searchtype=author&query=Massetti%2C+G+M">Greta M. Massetti</a>, <a href="/search/?searchtype=author&query=Demissie%2C+Z">Zewditu Demissie</a>, <a href="/search/?searchtype=author&query=Mercy%2C+J+A">James A. Mercy</a>, <a href="/search/?searchtype=author&query=Nelson%2C+C+A">Charles A. Nelson III</a>, <a href="/search/?searchtype=author&query=Cluver%2C+L">Lucie Cluver</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sherr%2C+L">Lorraine Sherr</a>, <a href="/search/?searchtype=author&query=Donnelly%2C+C+A">Christl A. Donnelly</a>, <a href="/search/?searchtype=author&query=Ratmann%2C+O">Oliver Ratmann</a>, <a href="/search/?searchtype=author&query=Unwin%2C+H+J+T">H. Juliette T. Unwin</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="2112.11777v1-abstract-short" style="display: inline;"> Background: Most COVID-19 deaths occur among adults, not children, and attention has focused on mitigating COVID-19 burden among adults. However, a tragic consequence of adult deaths is that high numbers of children might lose their parents and caregivers to COVID-19-associated deaths. Methods: We quantified COVID-19-associated caregiver loss and orphanhood in the US and for each state using fer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.11777v1-abstract-full').style.display = 'inline'; document.getElementById('2112.11777v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.11777v1-abstract-full" style="display: none;"> Background: Most COVID-19 deaths occur among adults, not children, and attention has focused on mitigating COVID-19 burden among adults. However, a tragic consequence of adult deaths is that high numbers of children might lose their parents and caregivers to COVID-19-associated deaths. Methods: We quantified COVID-19-associated caregiver loss and orphanhood in the US and for each state using fertility and excess and COVID-19 mortality data. We assessed burden and rates of COVID-19-associated orphanhood and deaths of custodial and co-residing grandparents, overall and by race/ethnicity. We further examined variations in COVID-19-associated orphanhood by race/ethnicity for each state. Results: We found that from April 1, 2020 through June 30, 2021, over 140,000 children in the US experienced the death of a parent or grandparent caregiver. The risk of such loss was 1.1 to 4.5 times higher among children of racial and ethnic minorities, compared to Non-Hispanic White children. The highest burden of COVID-19-associated death of parents and caregivers occurred in Southern border states for Hispanic children, Southeastern states for Black children, and in states with tribal areas for American Indian/Alaska Native populations. Conclusions: We found substantial disparities in distributions of COVID-19-associated death of parents and caregivers across racial and ethnic groups. Children losing caregivers to COVID-19 need care and safe, stable, and nurturing families with economic support, quality childcare and evidence-based parenting support programs. There is an urgent need to mount an evidence-based comprehensive response focused on those children at greatest risk, in the states most affected. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.11777v1-abstract-full').style.display = 'none'; document.getElementById('2112.11777v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 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/2110.12461">arXiv:2110.12461</a> <span> [<a href="https://arxiv.org/pdf/2110.12461">pdf</a>, <a href="https://arxiv.org/format/2110.12461">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Epidemia: An R Package for Semi-Mechanistic Bayesian Modelling of Infectious Diseases using Point Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Scott%2C+J+A">James A. Scott</a>, <a href="/search/?searchtype=author&query=Gandy%2C+A">Axel Gandy</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Unwin%2C+H+J+T">H. Juliette T. Unwin</a>, <a href="/search/?searchtype=author&query=Ish-Horowicz%2C+J">Jonathan Ish-Horowicz</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="2110.12461v1-abstract-short" style="display: inline;"> This article introduces epidemia, an R package for Bayesian, regression-oriented modeling of infectious diseases. The implemented models define a likelihood for all observed data while also explicitly modeling transmission dynamics: an approach often termed as semi-mechanistic. Infections are propagated over time using renewal equations. This approach is inspired by self-exciting, continuous-time… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.12461v1-abstract-full').style.display = 'inline'; document.getElementById('2110.12461v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.12461v1-abstract-full" style="display: none;"> This article introduces epidemia, an R package for Bayesian, regression-oriented modeling of infectious diseases. The implemented models define a likelihood for all observed data while also explicitly modeling transmission dynamics: an approach often termed as semi-mechanistic. Infections are propagated over time using renewal equations. This approach is inspired by self-exciting, continuous-time point processes such as the Hawkes process. A variety of inferential tasks can be performed using the package. Key epidemiological quantities, including reproduction numbers and latent infections, may be estimated within the framework. The models may be used to evaluate the determinants of changes in transmission rates, including the effects of control measures. Epidemic dynamics may be simulated either from a fitted model or a prior model; allowing for prior/posterior predictive checks, experimentation, and forecasting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.12461v1-abstract-full').style.display = 'none'; document.getElementById('2110.12461v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.10422">arXiv:2110.10422</a> <span> [<a href="https://arxiv.org/pdf/2110.10422">pdf</a>, <a href="https://arxiv.org/format/2110.10422">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 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/10.1098/rsif.2022.0094">10.1098/rsif.2022.0094 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> PriorVAE: Encoding spatial priors with VAEs for small-area estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Semenova%2C+E">Elizaveta Semenova</a>, <a href="/search/?searchtype=author&query=Xu%2C+Y">Yidan Xu</a>, <a href="/search/?searchtype=author&query=Howes%2C+A">Adam Howes</a>, <a href="/search/?searchtype=author&query=Rashid%2C+T">Theo Rashid</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2110.10422v3-abstract-short" style="display: inline;"> Gaussian processes (GPs), implemented through multivariate Gaussian distributions for a finite collection of data, are the most popular approach in small-area spatial statistical modelling. In this context they are used to encode correlation structures over space and can generalise well in interpolation tasks. Despite their flexibility, off-the-shelf GPs present serious computational challenges wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.10422v3-abstract-full').style.display = 'inline'; document.getElementById('2110.10422v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.10422v3-abstract-full" style="display: none;"> Gaussian processes (GPs), implemented through multivariate Gaussian distributions for a finite collection of data, are the most popular approach in small-area spatial statistical modelling. In this context they are used to encode correlation structures over space and can generalise well in interpolation tasks. Despite their flexibility, off-the-shelf GPs present serious computational challenges which limit their scalability and practical usefulness in applied settings. Here, we propose a novel, deep generative modelling approach to tackle this challenge, termed PriorVAE: for a particular spatial setting, we approximate a class of GP priors through prior sampling and subsequent fitting of a variational autoencoder (VAE). Given a trained VAE, the resultant decoder allows spatial inference to become incredibly efficient due to the low dimensional, independently distributed latent Gaussian space representation of the VAE. Once trained, inference using the VAE decoder replaces the GP within a Bayesian sampling framework. This approach provides tractable and easy-to-implement means of approximately encoding spatial priors and facilitates efficient statistical inference. We demonstrate the utility of our VAE two stage approach on Bayesian, small-area estimation tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.10422v3-abstract-full').style.display = 'none'; document.getElementById('2110.10422v3-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> 16 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.12360">arXiv:2106.12360</a> <span> [<a href="https://arxiv.org/pdf/2106.12360">pdf</a>, <a href="https://arxiv.org/format/2106.12360">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> </div> </div> <p class="title is-5 mathjax"> Regularised B-splines projected Gaussian Process priors to estimate time-trends of age-specific COVID-19 deaths related to vaccine roll-out </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Monod%2C+M">M茅lodie Monod</a>, <a href="/search/?searchtype=author&query=Blenkinsop%2C+A">Alexandra Blenkinsop</a>, <a href="/search/?searchtype=author&query=Brizzi%2C+A">Andrea Brizzi</a>, <a href="/search/?searchtype=author&query=Chen%2C+Y">Yu Chen</a>, <a href="/search/?searchtype=author&query=Perello%2C+C+C+C">Carlos Cardoso Correia Perello</a>, <a href="/search/?searchtype=author&query=Jogarah%2C+V">Vidoushee Jogarah</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yuanrong Wang</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Ratmann%2C+O">Oliver Ratmann</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="2106.12360v2-abstract-short" style="display: inline;"> The COVID-19 pandemic has caused severe public health consequences in the United States. In this study, we use a hierarchical Bayesian model to estimate the age-specific COVID-19 attributable deaths over time in the United States. The model is specified by a novel non-parametric spatial approach, a low-rank Gaussian Process (GP) projected by regularised B-splines. We show that this projection defi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.12360v2-abstract-full').style.display = 'inline'; document.getElementById('2106.12360v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.12360v2-abstract-full" style="display: none;"> The COVID-19 pandemic has caused severe public health consequences in the United States. In this study, we use a hierarchical Bayesian model to estimate the age-specific COVID-19 attributable deaths over time in the United States. The model is specified by a novel non-parametric spatial approach, a low-rank Gaussian Process (GP) projected by regularised B-splines. We show that this projection defines a new GP with attractive smoothness and computational efficiency properties, derive its kernel function, and discuss the penalty terms induced by the projected GP. Simulation analyses and benchmark results show that the spatial approach performs better than standard B-splines and Bayesian P-splines and equivalently well as a standard GP, for considerably lower runtimes. The B-splines projected GP priors that we develop are likely an appealing addition to the arsenal of Bayesian regularising priors. We apply the model to weekly, age-stratified COVID-19 attributable deaths reported by the US Centers for Disease Control, which are subject to censoring and reporting biases. Using the B-splines projected GP, we can estimate longitudinal trends in COVID-19 associated deaths across the US by 1-year age bands. These estimates are instrumental to calculate age-specific mortality rates, describe variation in age-specific deaths across the US, and for fitting epidemic models. Here, we couple the model with age-specific vaccination rates to show that lower vaccination rates in younger adults aged 18-64 are associated with significantly stronger resurgences in COVID-19 deaths, especially in Florida and Texas. These results underscore the critical importance of medically able individuals of all ages to be vaccinated against COVID-19 in order to limit fatal outcomes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.12360v2-abstract-full').style.display = 'none'; document.getElementById('2106.12360v2-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 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/2106.05818">arXiv:2106.05818</a> <span> [<a href="https://arxiv.org/pdf/2106.05818">pdf</a>, <a href="https://arxiv.org/format/2106.05818">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> </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/10.1038/s41586-021-04198-4">10.1038/s41586-021-04198-4 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Unrepresentative Big Surveys Significantly Overestimate US Vaccine Uptake </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Bradley%2C+V+C">Valerie C. Bradley</a>, <a href="/search/?searchtype=author&query=Kuriwaki%2C+S">Shiro Kuriwaki</a>, <a href="/search/?searchtype=author&query=Isakov%2C+M">Michael Isakov</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a>, <a href="/search/?searchtype=author&query=Meng%2C+X">Xiao-Li Meng</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2106.05818v3-abstract-short" style="display: inline;"> Surveys are a crucial tool for understanding public opinion and behavior, and their accuracy depends on maintaining statistical representativeness of their target populations by minimizing biases from all sources. Increasing data size shrinks confidence intervals but magnifies the impact of survey bias, an instance of the Big Data Paradox (Meng 2018). Here we demonstrate this paradox in estimates… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.05818v3-abstract-full').style.display = 'inline'; document.getElementById('2106.05818v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.05818v3-abstract-full" style="display: none;"> Surveys are a crucial tool for understanding public opinion and behavior, and their accuracy depends on maintaining statistical representativeness of their target populations by minimizing biases from all sources. Increasing data size shrinks confidence intervals but magnifies the impact of survey bias, an instance of the Big Data Paradox (Meng 2018). Here we demonstrate this paradox in estimates of first-dose COVID-19 vaccine uptake in US adults: Delphi-Facebook (about 250,000 responses per week) and Census Household Pulse (about 75,000 per week). By May 2021, Delphi-Facebook overestimated uptake by 17 percentage points and Census Household Pulse by 14, compared to a benchmark from the Centers for Disease Control and Prevention (CDC). Moreover, their large data sizes led to minuscule margins of error on the incorrect estimates. In contrast, an Axios-Ipsos online panel with about 1,000 responses following survey research best practices (AAPOR) provided reliable estimates and uncertainty. We decompose observed error using a recent analytic framework to explain the inaccuracy in the three surveys. We then analyze the implications for vaccine hesitancy and willingness. We show how a survey of 250,000 respondents can produce an estimate of the population mean that is no more accurate than an estimate from a simple random sample of size 10. Our central message is that data quality matters far more than data quantity, and compensating the former with the latter is a mathematically provable losing proposition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.05818v3-abstract-full').style.display = 'none'; document.getElementById('2106.05818v3-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">Revised and reformatted for journal</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Nature 600, 695-700 (2021) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.01460">arXiv:2105.01460</a> <span> [<a href="https://arxiv.org/pdf/2105.01460">pdf</a>, <a href="https://arxiv.org/format/2105.01460">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="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Aggregated Gaussian Processes with Multiresolution Earth Observation Covariates </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhu%2C+H">Harrison Zhu</a>, <a href="/search/?searchtype=author&query=Howes%2C+A">Adam Howes</a>, <a href="/search/?searchtype=author&query=van+Eer%2C+O">Owen van Eer</a>, <a href="/search/?searchtype=author&query=Rischard%2C+M">Maxime Rischard</a>, <a href="/search/?searchtype=author&query=Li%2C+Y">Yingzhen Li</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="2105.01460v2-abstract-short" style="display: inline;"> For many survey-based spatial modelling problems, responses are observed as spatially aggregated over survey regions due to limited resources. Covariates, from weather models and satellite imageries, can be observed at many different spatial resolutions, making the pre-processing of covariates a key challenge for any spatial modelling task. We propose a Gaussian process regression model to flexibl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.01460v2-abstract-full').style.display = 'inline'; document.getElementById('2105.01460v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.01460v2-abstract-full" style="display: none;"> For many survey-based spatial modelling problems, responses are observed as spatially aggregated over survey regions due to limited resources. Covariates, from weather models and satellite imageries, can be observed at many different spatial resolutions, making the pre-processing of covariates a key challenge for any spatial modelling task. We propose a Gaussian process regression model to flexibly handle multiresolution covariates by employing an additive kernel that can efficiently aggregate features across resolutions. Compared to existing approaches that rely on resolution matching, our approach better maintains distributional information across resolutions, leading to better performance and interpretability. Our model yields stronger predictive performance and interpretability on both simulated and crop yield datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.01460v2-abstract-full').style.display = 'none'; document.getElementById('2105.01460v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.08341">arXiv:2103.08341</a> <span> [<a href="https://arxiv.org/pdf/2103.08341">pdf</a>, <a href="https://arxiv.org/format/2103.08341">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="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Evaluating distributional regression strategies for modelling self-reported sexual age-mixing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wolock%2C+T+M">Timothy M Wolock</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S+R">Seth R Flaxman</a>, <a href="/search/?searchtype=author&query=Risher%2C+K+A">Kathryn A Risher</a>, <a href="/search/?searchtype=author&query=Dadirai%2C+T">Tawanda Dadirai</a>, <a href="/search/?searchtype=author&query=Gregson%2C+S">Simon Gregson</a>, <a href="/search/?searchtype=author&query=Eaton%2C+J+W">Jeffrey W Eaton</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="2103.08341v1-abstract-short" style="display: inline;"> The age dynamics of sexual partnership formation determine patterns of sexually transmitted disease transmission and have long been a focus of researchers studying human immunodeficiency virus. Data on self-reported sexual partner age distributions are available from a variety of sources. We sought to explore statistical models that accurately predict the distribution of sexual partner ages over a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.08341v1-abstract-full').style.display = 'inline'; document.getElementById('2103.08341v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.08341v1-abstract-full" style="display: none;"> The age dynamics of sexual partnership formation determine patterns of sexually transmitted disease transmission and have long been a focus of researchers studying human immunodeficiency virus. Data on self-reported sexual partner age distributions are available from a variety of sources. We sought to explore statistical models that accurately predict the distribution of sexual partner ages over age and sex. We identified which probability distributions and outcome specifications best captured variation in partner age and quantified the benefits of modelling these data using distributional regression. We found that distributional regression with a sinh-arcsinh distribution replicated observed partner age distributions most accurately across three geographically diverse data sets. This framework can be extended with well-known hierarchical modelling tools and can help improve estimates of sexual age-mixing dynamics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.08341v1-abstract-full').style.display = 'none'; document.getElementById('2103.08341v1-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">Main text: 25 pages, 7 figures, 5 tables; Appendix: 24 pages, 11 figures, 10 tables; Submitted to eLife</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.11249">arXiv:2102.11249</a> <span> [<a href="https://arxiv.org/pdf/2102.11249">pdf</a>, <a href="https://arxiv.org/format/2102.11249">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Gaussian Process Nowcasting: Application to COVID-19 Mortality Reporting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hawryluk%2C+I">Iwona Hawryluk</a>, <a href="/search/?searchtype=author&query=Hoeltgebaum%2C+H">Henrique Hoeltgebaum</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Miscouridou%2C+X">Xenia Miscouridou</a>, <a href="/search/?searchtype=author&query=Schnekenberg%2C+R+P">Ricardo P Schnekenberg</a>, <a href="/search/?searchtype=author&query=Whittaker%2C+C">Charles Whittaker</a>, <a href="/search/?searchtype=author&query=Vollmer%2C+M">Michaela Vollmer</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Mellan%2C+T+A">Thomas A Mellan</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="2102.11249v2-abstract-short" style="display: inline;"> Updating observations of a signal due to the delays in the measurement process is a common problem in signal processing, with prominent examples in a wide range of fields. An important example of this problem is the nowcasting of COVID-19 mortality: given a stream of reported counts of daily deaths, can we correct for the delays in reporting to paint an accurate picture of the present, with uncert… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.11249v2-abstract-full').style.display = 'inline'; document.getElementById('2102.11249v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.11249v2-abstract-full" style="display: none;"> Updating observations of a signal due to the delays in the measurement process is a common problem in signal processing, with prominent examples in a wide range of fields. An important example of this problem is the nowcasting of COVID-19 mortality: given a stream of reported counts of daily deaths, can we correct for the delays in reporting to paint an accurate picture of the present, with uncertainty? Without this correction, raw data will often mislead by suggesting an improving situation. We present a flexible approach using a latent Gaussian process that is capable of describing the changing auto-correlation structure present in the reporting time-delay surface. This approach also yields robust estimates of uncertainty for the estimated nowcasted numbers of deaths. We test assumptions in model specification such as the choice of kernel or hyper priors, and evaluate model performance on a challenging real dataset from Brazil. Our experiments show that Gaussian process nowcasting performs favourably against both comparable methods, and against a small sample of expert human predictions. Our approach has substantial practical utility in disease modelling -- by applying our approach to COVID-19 mortality data from Brazil, where reporting delays are large, we can make informative predictions on important epidemiological quantities such as the current effective reproduction number. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.11249v2-abstract-full').style.display = 'none'; document.getElementById('2102.11249v2-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 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">26 pages, 31 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/2012.00394">arXiv:2012.00394</a> <span> [<a href="https://arxiv.org/pdf/2012.00394">pdf</a>, <a href="https://arxiv.org/format/2012.00394">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="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Semi-Mechanistic Bayesian Modeling of COVID-19 with Renewal Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Ferguson%2C+N">Neil Ferguson</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Gandy%2C+A">Axel Gandy</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Scott%2C+J+A">James A. Scott</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="2012.00394v2-abstract-short" style="display: inline;"> We propose a general Bayesian approach to modeling epidemics such as COVID-19. The approach grew out of specific analyses conducted during the pandemic, in particular an analysis concerning the effects of non-pharmaceutical interventions (NPIs) in reducing COVID-19 transmission in 11 European countries. The model parameterizes the time varying reproduction number $R_t$ through a regression framewo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.00394v2-abstract-full').style.display = 'inline'; document.getElementById('2012.00394v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.00394v2-abstract-full" style="display: none;"> We propose a general Bayesian approach to modeling epidemics such as COVID-19. The approach grew out of specific analyses conducted during the pandemic, in particular an analysis concerning the effects of non-pharmaceutical interventions (NPIs) in reducing COVID-19 transmission in 11 European countries. The model parameterizes the time varying reproduction number $R_t$ through a regression framework in which covariates can e.g be governmental interventions or changes in mobility patterns. This allows a joint fit across regions and partial pooling to share strength. This innovation was critical to our timely estimates of the impact of lockdown and other NPIs in the European epidemics, whose validity was borne out by the subsequent course of the epidemic. Our framework provides a fully generative model for latent infections and observations deriving from them, including deaths, cases, hospitalizations, ICU admissions and seroprevalence surveys. One issue surrounding our model's use during the COVID-19 pandemic is the confounded nature of NPIs and mobility. We use our framework to explore this issue. We have open sourced an R package epidemia implementing our approach in Stan. Versions of the model are used by New York State, Tennessee and Scotland to estimate the current situation and make policy decisions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.00394v2-abstract-full').style.display = 'none'; document.getElementById('2012.00394v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.03851">arXiv:2009.03851</a> <span> [<a href="https://arxiv.org/pdf/2009.03851">pdf</a>, <a href="https://arxiv.org/format/2009.03851">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Referenced Thermodynamic Integration for Bayesian Model Selection: Application to COVID-19 Model Selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hawryluk%2C+I">Iwona Hawryluk</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Mellan%2C+T+A">Thomas A. Mellan</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="2009.03851v3-abstract-short" style="display: inline;"> Model selection is a fundamental part of the applied Bayesian statistical methodology. Metrics such as the Akaike Information Criterion are commonly used in practice to select models but do not incorporate the uncertainty of the models' parameters and can give misleading choices. One approach that uses the full posterior distribution is to compute the ratio of two models' normalising constants, kn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.03851v3-abstract-full').style.display = 'inline'; document.getElementById('2009.03851v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.03851v3-abstract-full" style="display: none;"> Model selection is a fundamental part of the applied Bayesian statistical methodology. Metrics such as the Akaike Information Criterion are commonly used in practice to select models but do not incorporate the uncertainty of the models' parameters and can give misleading choices. One approach that uses the full posterior distribution is to compute the ratio of two models' normalising constants, known as the Bayes factor. Often in realistic problems, this involves the integration of analytically intractable, high-dimensional distributions, and therefore requires the use of stochastic methods such as thermodynamic integration (TI). In this paper we apply a variation of the TI method, referred to as referenced TI, which computes a single model's normalising constant in an efficient way by using a judiciously chosen reference density. The advantages of the approach and theoretical considerations are set out, along with explicit pedagogical 1 and 2D examples. Benchmarking is presented with comparable methods and we find favourable convergence performance. The approach is shown to be useful in practice when applied to a real problem - to perform model selection for a semi-mechanistic hierarchical Bayesian model of COVID-19 transmission in South Korea involving the integration of a 200D density. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.03851v3-abstract-full').style.display = 'none'; document.getElementById('2009.03851v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 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">27 pages, 8 figures, 3 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/2009.02264">arXiv:2009.02264</a> <span> [<a href="https://arxiv.org/pdf/2009.02264">pdf</a>, <a href="https://arxiv.org/format/2009.02264">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biological Physics">physics.bio-ph</span> </div> </div> <p class="title is-5 mathjax"> Improving axial resolution in SIM using deep learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Boland%2C+M">Miguel Boland</a>, <a href="/search/?searchtype=author&query=Cohen%2C+E+A+K">Edward A. K. Cohen</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Neil%2C+M+A+A">Mark A. A. Neil</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="2009.02264v3-abstract-short" style="display: inline;"> Structured Illumination Microscopy is a widespread methodology to image live and fixed biological structures smaller than the diffraction limits of conventional optical microscopy. Using recent advances in image up-scaling through deep learning models, we demonstrate a method to reconstruct 3D SIM image stacks with twice the axial resolution attainable through conventional SIM reconstructions. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.02264v3-abstract-full').style.display = 'inline'; document.getElementById('2009.02264v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.02264v3-abstract-full" style="display: none;"> Structured Illumination Microscopy is a widespread methodology to image live and fixed biological structures smaller than the diffraction limits of conventional optical microscopy. Using recent advances in image up-scaling through deep learning models, we demonstrate a method to reconstruct 3D SIM image stacks with twice the axial resolution attainable through conventional SIM reconstructions. We further evaluate our method for robustness to noise & generalisability to varying observed specimens, and discuss potential adaptions of the method to further improvements in resolution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.02264v3-abstract-full').style.display = 'none'; document.getElementById('2009.02264v3-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> 18 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 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">ACM Class:</span> I.4.5; I.2.10 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.10317">arXiv:2007.10317</a> <span> [<a href="https://arxiv.org/pdf/2007.10317">pdf</a>, <a href="https://arxiv.org/format/2007.10317">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Populations and Evolution">q-bio.PE</span> </div> </div> <p class="title is-5 mathjax"> Inference of COVID-19 epidemiological distributions from Brazilian hospital data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hawryluk%2C+I">Iwona Hawryluk</a>, <a href="/search/?searchtype=author&query=Mellan%2C+T+A">Thomas A. Mellan</a>, <a href="/search/?searchtype=author&query=Hoeltgebaum%2C+H+H">Henrique H. Hoeltgebaum</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Schnekenberg%2C+R+P">Ricardo P. Schnekenberg</a>, <a href="/search/?searchtype=author&query=Whittaker%2C+C">Charles Whittaker</a>, <a href="/search/?searchtype=author&query=Zhu%2C+H">Harrison Zhu</a>, <a href="/search/?searchtype=author&query=Gandy%2C+A">Axel Gandy</a>, <a href="/search/?searchtype=author&query=Donnelly%2C+C+A">Christl A. Donnelly</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</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="2007.10317v2-abstract-short" style="display: inline;"> Knowing COVID-19 epidemiological distributions, such as the time from patient admission to death, is directly relevant to effective primary and secondary care planning, and moreover, the mathematical modelling of the pandemic generally. We determine epidemiological distributions for patients hospitalised with COVID-19 using a large dataset ($N=21{,}000-157{,}000$) from the Brazilian Sistema de Inf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.10317v2-abstract-full').style.display = 'inline'; document.getElementById('2007.10317v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.10317v2-abstract-full" style="display: none;"> Knowing COVID-19 epidemiological distributions, such as the time from patient admission to death, is directly relevant to effective primary and secondary care planning, and moreover, the mathematical modelling of the pandemic generally. We determine epidemiological distributions for patients hospitalised with COVID-19 using a large dataset ($N=21{,}000-157{,}000$) from the Brazilian Sistema de Informa莽茫o de Vigil芒ncia Epidemiol贸gica da Gripe database. A joint Bayesian subnational model with partial pooling is used to simultaneously describe the 26 states and one federal district of Brazil, and shows significant variation in the mean of the symptom-onset-to-death time, with ranges between 11.2-17.8 days across the different states, and a mean of 15.2 days for Brazil. We find strong evidence in favour of specific probability density function choices: for example, the gamma distribution gives the best fit for onset-to-death and the generalised log-normal for onset-to-hospital-admission. Our results show that epidemiological distributions have considerable geographical variation, and provide the first estimates of these distributions in a low and middle-income setting. At the subnational level, variation in COVID-19 outcome timings are found to be correlated with poverty, deprivation and segregation levels, and weaker correlation is observed for mean age, wealth and urbanicity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.10317v2-abstract-full').style.display = 'none'; document.getElementById('2007.10317v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.06566">arXiv:2007.06566</a> <span> [<a href="https://arxiv.org/pdf/2007.06566">pdf</a>, <a href="https://arxiv.org/format/2007.06566">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <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"> A unified machine learning approach to time series forecasting applied to demand at emergency departments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Vollmer%2C+M+A+C">Michaela A. C. Vollmer</a>, <a href="/search/?searchtype=author&query=Glampson%2C+B">Ben Glampson</a>, <a href="/search/?searchtype=author&query=Mellan%2C+T+A">Thomas A. Mellan</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Mercuri%2C+L">Luca Mercuri</a>, <a href="/search/?searchtype=author&query=Costello%2C+C">Ceire Costello</a>, <a href="/search/?searchtype=author&query=Klaber%2C+R">Robert Klaber</a>, <a href="/search/?searchtype=author&query=Cooke%2C+G">Graham Cooke</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</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="2007.06566v1-abstract-short" style="display: inline;"> There were 25.6 million attendances at Emergency Departments (EDs) in England in 2019 corresponding to an increase of 12 million attendances over the past ten years. The steadily rising demand at EDs creates a constant challenge to provide adequate quality of care while maintaining standards and productivity. Managing hospital demand effectively requires an adequate knowledge of the future rate of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.06566v1-abstract-full').style.display = 'inline'; document.getElementById('2007.06566v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.06566v1-abstract-full" style="display: none;"> There were 25.6 million attendances at Emergency Departments (EDs) in England in 2019 corresponding to an increase of 12 million attendances over the past ten years. The steadily rising demand at EDs creates a constant challenge to provide adequate quality of care while maintaining standards and productivity. Managing hospital demand effectively requires an adequate knowledge of the future rate of admission. Using 8 years of electronic admissions data from two major acute care hospitals in London, we develop a novel ensemble methodology that combines the outcomes of the best performing time series and machine learning approaches in order to make highly accurate forecasts of demand, 1, 3 and 7 days in the future. Both hospitals face an average daily demand of 208 and 106 attendances respectively and experience considerable volatility around this mean. However, our approach is able to predict attendances at these emergency departments one day in advance up to a mean absolute error of +/- 14 and +/- 10 patients corresponding to a mean absolute percentage error of 6.8% and 8.6% respectively. Our analysis compares machine learning algorithms to more traditional linear models. We find that linear models often outperform machine learning methods and that the quality of our predictions for any of the forecasting horizons of 1, 3 or 7 days are comparable as measured in MAE. In addition to comparing and combining state-of-the-art forecasting methods to predict hospital demand, we consider two different hyperparameter tuning methods, enabling a faster deployment of our models without compromising performance. We believe our framework can readily be used to forecast a wide range of policy relevant indicators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.06566v1-abstract-full').style.display = 'none'; document.getElementById('2007.06566v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.16487">arXiv:2006.16487</a> <span> [<a href="https://arxiv.org/pdf/2006.16487">pdf</a>, <a href="https://arxiv.org/format/2006.16487">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Populations and Evolution">q-bio.PE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> On the derivation of the renewal equation from an age-dependent branching process: an epidemic modelling perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Berah%2C+T">Tresnia Berah</a>, <a href="/search/?searchtype=author&query=Mellan%2C+T+A">Thomas A. Mellan</a>, <a href="/search/?searchtype=author&query=Unwin%2C+H+J+T">H. Juliette T. Unwin</a>, <a href="/search/?searchtype=author&query=Vollmer%2C+M+A">Michaela A Vollmer</a>, <a href="/search/?searchtype=author&query=Parag%2C+K+V">Kris V Parag</a>, <a href="/search/?searchtype=author&query=Gandy%2C+A">Axel Gandy</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</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="2006.16487v1-abstract-short" style="display: inline;"> Renewal processes are a popular approach used in modelling infectious disease outbreaks. In a renewal process, previous infections give rise to future infections. However, while this formulation seems sensible, its application to infectious disease can be difficult to justify from first principles. It has been shown from the seminal work of Bellman and Harris that the renewal equation arises as th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.16487v1-abstract-full').style.display = 'inline'; document.getElementById('2006.16487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.16487v1-abstract-full" style="display: none;"> Renewal processes are a popular approach used in modelling infectious disease outbreaks. In a renewal process, previous infections give rise to future infections. However, while this formulation seems sensible, its application to infectious disease can be difficult to justify from first principles. It has been shown from the seminal work of Bellman and Harris that the renewal equation arises as the expectation of an age-dependent branching process. In this paper we provide a detailed derivation of the original Bellman Harris process. We introduce generalisations, that allow for time-varying reproduction numbers and the accounting of exogenous events, such as importations. We show how inference on the renewal equation is easy to accomplish within a Bayesian hierarchical framework. Using off the shelf MCMC packages, we fit to South Korea COVID-19 case data to estimate reproduction numbers and importations. Our derivation provides the mathematical fundamentals and assumptions underpinning the use of the renewal equation for modelling outbreaks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.16487v1-abstract-full').style.display = 'none'; document.getElementById('2006.16487v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.05371">arXiv:2006.05371</a> <span> [<a href="https://arxiv.org/pdf/2006.05371">pdf</a>, <a href="https://arxiv.org/format/2006.05371">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</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"> Bayesian Probabilistic Numerical Integration with Tree-Based Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhu%2C+H">Harrison Zhu</a>, <a href="/search/?searchtype=author&query=Liu%2C+X">Xing Liu</a>, <a href="/search/?searchtype=author&query=Kang%2C+R">Ruya Kang</a>, <a href="/search/?searchtype=author&query=Shen%2C+Z">Zhichao Shen</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Briol%2C+F">Fran莽ois-Xavier Briol</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="2006.05371v3-abstract-short" style="display: inline;"> Bayesian quadrature (BQ) is a method for solving numerical integration problems in a Bayesian manner, which allows users to quantify their uncertainty about the solution. The standard approach to BQ is based on a Gaussian process (GP) approximation of the integrand. As a result, BQ is inherently limited to cases where GP approximations can be done in an efficient manner, thus often prohibiting ver… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.05371v3-abstract-full').style.display = 'inline'; document.getElementById('2006.05371v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.05371v3-abstract-full" style="display: none;"> Bayesian quadrature (BQ) is a method for solving numerical integration problems in a Bayesian manner, which allows users to quantify their uncertainty about the solution. The standard approach to BQ is based on a Gaussian process (GP) approximation of the integrand. As a result, BQ is inherently limited to cases where GP approximations can be done in an efficient manner, thus often prohibiting very high-dimensional or non-smooth target functions. This paper proposes to tackle this issue with a new Bayesian numerical integration algorithm based on Bayesian Additive Regression Trees (BART) priors, which we call BART-Int. BART priors are easy to tune and well-suited for discontinuous functions. We demonstrate that they also lend themselves naturally to a sequential design setting and that explicit convergence rates can be obtained in a variety of settings. The advantages and disadvantages of this new methodology are highlighted on a set of benchmark tests including the Genz functions, and on a Bayesian survey design problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.05371v3-abstract-full').style.display = 'none'; document.getElementById('2006.05371v3-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">v1</span> submitted 9 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.10123">arXiv:2005.10123</a> <span> [<a href="https://arxiv.org/pdf/2005.10123">pdf</a>, <a href="https://arxiv.org/format/2005.10123">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> </div> </div> <p class="title is-5 mathjax"> Scalable Bayesian inference for self-excitatory stochastic processes applied to big American gunfire data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Holbrook%2C+A+J">Andrew J. Holbrook</a>, <a href="/search/?searchtype=author&query=Loeffler%2C+C+E">Charles E. Loeffler</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S+R">Seth R. Flaxman</a>, <a href="/search/?searchtype=author&query=Suchard%2C+M+A">Marc A. Suchard</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="2005.10123v1-abstract-short" style="display: inline;"> The Hawkes process and its extensions effectively model self-excitatory phenomena including earthquakes, viral pandemics, financial transactions, neural spike trains and the spread of memes through social networks. The usefulness of these stochastic process models within a host of economic sectors and scientific disciplines is undercut by the processes' computational burden: complexity of likeliho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.10123v1-abstract-full').style.display = 'inline'; document.getElementById('2005.10123v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.10123v1-abstract-full" style="display: none;"> The Hawkes process and its extensions effectively model self-excitatory phenomena including earthquakes, viral pandemics, financial transactions, neural spike trains and the spread of memes through social networks. The usefulness of these stochastic process models within a host of economic sectors and scientific disciplines is undercut by the processes' computational burden: complexity of likelihood evaluations grows quadratically in the number of observations for both the temporal and spatiotemporal Hawkes processes. We show that, with care, one may parallelize these calculations using both central and graphics processing unit implementations to achieve over 100-fold speedups over single-core processing. Using a simple adaptive Metropolis-Hastings scheme, we apply our high-performance computing framework to a Bayesian analysis of big gunshot data generated in Washington D.C. between the years of 2006 and 2019, thereby extending a past analysis of the same data from under 10,000 to over 85,000 observations. To encourage wide-spread use, we provide hpHawkes, an open-source R package, and discuss high-level implementation and program design for leveraging aspects of computational hardware that become necessary in a big data setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.10123v1-abstract-full').style.display = 'none'; document.getElementById('2005.10123v1-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 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Submitted to Statistics and Computing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.07927">arXiv:2005.07927</a> <span> [<a href="https://arxiv.org/pdf/2005.07927">pdf</a>, <a href="https://arxiv.org/format/2005.07927">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.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"> BART-based inference for Poisson processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lamprinakou%2C+S">Stamatina Lamprinakou</a>, <a href="/search/?searchtype=author&query=Barahona%2C+M">Mauricio Barahona</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Filippi%2C+S">Sarah Filippi</a>, <a href="/search/?searchtype=author&query=Gandy%2C+A">Axel Gandy</a>, <a href="/search/?searchtype=author&query=McCoy%2C+E">Emma McCoy</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="2005.07927v2-abstract-short" style="display: inline;"> The effectiveness of Bayesian Additive Regression Trees (BART) has been demonstrated in a variety of contexts including non-parametric regression and classification. A BART scheme for estimating the intensity of inhomogeneous Poisson processes is introduced. Poisson intensity estimation is a vital task in various applications including medical imaging, astrophysics and network traffic analysis. Th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.07927v2-abstract-full').style.display = 'inline'; document.getElementById('2005.07927v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.07927v2-abstract-full" style="display: none;"> The effectiveness of Bayesian Additive Regression Trees (BART) has been demonstrated in a variety of contexts including non-parametric regression and classification. A BART scheme for estimating the intensity of inhomogeneous Poisson processes is introduced. Poisson intensity estimation is a vital task in various applications including medical imaging, astrophysics and network traffic analysis. The new approach enables full posterior inference of the intensity in a non-parametric regression setting. The performance of the novel scheme is demonstrated through simulation studies on synthetic and real datasets up to five dimensions, and the new scheme is compared with alternative approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.07927v2-abstract-full').style.display = 'none'; document.getElementById('2005.07927v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Accepted version including Supplementary Material. To appear in Computational Statistics & Data Analysis (CSDA)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.11342">arXiv:2004.11342</a> <span> [<a href="https://arxiv.org/pdf/2004.11342">pdf</a>, <a href="https://arxiv.org/format/2004.11342">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="Populations and Evolution">q-bio.PE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Estimating the number of infections and the impact of non-pharmaceutical interventions on COVID-19 in European countries: technical description update </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Gandy%2C+A">Axel Gandy</a>, <a href="/search/?searchtype=author&query=Unwin%2C+H+J+T">H Juliette T Unwin</a>, <a href="/search/?searchtype=author&query=Coupland%2C+H">Helen Coupland</a>, <a href="/search/?searchtype=author&query=Mellan%2C+T+A">Thomas A Mellan</a>, <a href="/search/?searchtype=author&query=Zhu%2C+H">Harrison Zhu</a>, <a href="/search/?searchtype=author&query=Berah%2C+T">Tresnia Berah</a>, <a href="/search/?searchtype=author&query=Eaton%2C+J+W">Jeffrey W Eaton</a>, <a href="/search/?searchtype=author&query=Guzman%2C+P+N+P">Pablo N P Guzman</a>, <a href="/search/?searchtype=author&query=Schmit%2C+N">Nora Schmit</a>, <a href="/search/?searchtype=author&query=Callizo%2C+L">Lucia Callizo</a>, <a href="/search/?searchtype=author&query=Team%2C+I+C+C+R">Imperial College COVID-19 Response Team</a>, <a href="/search/?searchtype=author&query=Whittaker%2C+C">Charles Whittaker</a>, <a href="/search/?searchtype=author&query=Winskill%2C+P">Peter Winskill</a>, <a href="/search/?searchtype=author&query=Xi%2C+X">Xiaoyue Xi</a>, <a href="/search/?searchtype=author&query=Ghani%2C+A">Azra Ghani</a>, <a href="/search/?searchtype=author&query=Donnelly%2C+C+A">Christl A. Donnelly</a>, <a href="/search/?searchtype=author&query=Riley%2C+S">Steven Riley</a>, <a href="/search/?searchtype=author&query=Okell%2C+L+C">Lucy C Okell</a>, <a href="/search/?searchtype=author&query=Vollmer%2C+M+A+C">Michaela A C Vollmer</a>, <a href="/search/?searchtype=author&query=Ferguson%2C+N+M">Neil M. Ferguson</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</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="2004.11342v1-abstract-short" style="display: inline;"> Following the emergence of a novel coronavirus (SARS-CoV-2) and its spread outside of China, Europe has experienced large epidemics. In response, many European countries have implemented unprecedented non-pharmaceutical interventions including case isolation, the closure of schools and universities, banning of mass gatherings and/or public events, and most recently, wide-scale social distancing in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.11342v1-abstract-full').style.display = 'inline'; document.getElementById('2004.11342v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.11342v1-abstract-full" style="display: none;"> Following the emergence of a novel coronavirus (SARS-CoV-2) and its spread outside of China, Europe has experienced large epidemics. In response, many European countries have implemented unprecedented non-pharmaceutical interventions including case isolation, the closure of schools and universities, banning of mass gatherings and/or public events, and most recently, wide-scale social distancing including local and national lockdowns. In this technical update, we extend a semi-mechanistic Bayesian hierarchical model that infers the impact of these interventions and estimates the number of infections over time. Our methods assume that changes in the reproductive number - a measure of transmission - are an immediate response to these interventions being implemented rather than broader gradual changes in behaviour. Our model estimates these changes by calculating backwards from temporal data on observed to estimate the number of infections and rate of transmission that occurred several weeks prior, allowing for a probabilistic time lag between infection and death. In this update we extend our original model [Flaxman, Mishra, Gandy et al 2020, Report #13, Imperial College London] to include (a) population saturation effects, (b) prior uncertainty on the infection fatality ratio, (c) a more balanced prior on intervention effects and (d) partial pooling of the lockdown intervention covariate. We also (e) included another 3 countries (Greece, the Netherlands and Portugal). The model code is available at https://github.com/ImperialCollegeLondon/covid19model/ We are now reporting the results of our updated model online at https://mrc-ide.github.io/covid19estimates/ We estimated parameters jointly for all M=14 countries in a single hierarchical model. Inference is performed in the probabilistic programming language Stan using an adaptive Hamiltonian Monte Carlo (HMC) sampler. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.11342v1-abstract-full').style.display = 'none'; document.getElementById('2004.11342v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.06873">arXiv:2002.06873</a> <span> [<a href="https://arxiv.org/pdf/2002.06873">pdf</a>, <a href="https://arxiv.org/format/2002.06873">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"> $蟺$VAE: a stochastic process prior for Bayesian deep learning with MCMC </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Mishra%2C+S">Swapnil Mishra</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Berah%2C+T">Tresnia Berah</a>, <a href="/search/?searchtype=author&query=Zhu%2C+H">Harrison Zhu</a>, <a href="/search/?searchtype=author&query=Pakkanen%2C+M">Mikko Pakkanen</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</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="2002.06873v6-abstract-short" style="display: inline;"> Stochastic processes provide a mathematically elegant way model complex data. In theory, they provide flexible priors over function classes that can encode a wide range of interesting assumptions. In practice, however, efficient inference by optimisation or marginalisation is difficult, a problem further exacerbated with big data and high dimensional input spaces. We propose a novel variational au… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.06873v6-abstract-full').style.display = 'inline'; document.getElementById('2002.06873v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.06873v6-abstract-full" style="display: none;"> Stochastic processes provide a mathematically elegant way model complex data. In theory, they provide flexible priors over function classes that can encode a wide range of interesting assumptions. In practice, however, efficient inference by optimisation or marginalisation is difficult, a problem further exacerbated with big data and high dimensional input spaces. We propose a novel variational autoencoder (VAE) called the prior encoding variational autoencoder ($蟺$VAE). The $蟺$VAE is finitely exchangeable and Kolmogorov consistent, and thus is a continuous stochastic process. We use $蟺$VAE to learn low dimensional embeddings of function classes. We show that our framework can accurately learn expressive function classes such as Gaussian processes, but also properties of functions to enable statistical inference (such as the integral of a log Gaussian process). For popular tasks, such as spatial interpolation, $蟺$VAE achieves state-of-the-art performance both in terms of accuracy and computational efficiency. Perhaps most usefully, we demonstrate that the low dimensional independently distributed latent space representation learnt provides an elegant and scalable means of performing Bayesian inference for stochastic processes within probabilistic programming languages such as Stan. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.06873v6-abstract-full').style.display = 'none'; document.getElementById('2002.06873v6-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.05550">arXiv:2002.05550</a> <span> [<a href="https://arxiv.org/pdf/2002.05550">pdf</a>, <a href="https://arxiv.org/format/2002.05550">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</span> </div> </div> <p class="title is-5 mathjax"> Bayesian Kernel Two-Sample Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Zhang%2C+Q">Qinyi Zhang</a>, <a href="/search/?searchtype=author&query=Wild%2C+V">Veit Wild</a>, <a href="/search/?searchtype=author&query=Filippi%2C+S">Sarah Filippi</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</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="2002.05550v2-abstract-short" style="display: inline;"> In modern data analysis, nonparametric measures of discrepancies between random variables are particularly important. The subject is well-studied in the frequentist literature, while the development in the Bayesian setting is limited where applications are often restricted to univariate cases. Here, we propose a Bayesian kernel two-sample testing procedure based on modelling the difference between… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.05550v2-abstract-full').style.display = 'inline'; document.getElementById('2002.05550v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.05550v2-abstract-full" style="display: none;"> In modern data analysis, nonparametric measures of discrepancies between random variables are particularly important. The subject is well-studied in the frequentist literature, while the development in the Bayesian setting is limited where applications are often restricted to univariate cases. Here, we propose a Bayesian kernel two-sample testing procedure based on modelling the difference between kernel mean embeddings in the reproducing kernel Hilbert space utilising the framework established by Flaxman et al (2016). The use of kernel methods enables its application to random variables in generic domains beyond the multivariate Euclidean spaces. The proposed procedure results in a posterior inference scheme that allows an automatic selection of the kernel parameters relevant to the problem at hand. In a series of synthetic experiments and two real data experiments (i.e. testing network heterogeneity from high-dimensional data and six-membered monocyclic ring conformation comparison), we illustrate the advantages of our approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.05550v2-abstract-full').style.display = 'none'; document.getElementById('2002.05550v2-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.01590">arXiv:1912.01590</a> <span> [<a href="https://arxiv.org/pdf/1912.01590">pdf</a>, <a href="https://arxiv.org/format/1912.01590">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> </div> </div> <p class="title is-5 mathjax"> Inferring HIV incidence trends and transmission dynamics with a spatio-temporal HIV epidemic model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Wolock%2C+T+M">Timothy M Wolock</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S+R">Seth R Flaxman</a>, <a href="/search/?searchtype=author&query=Eaton%2C+J+W">Jeffrey W Eaton</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="1912.01590v1-abstract-short" style="display: inline;"> Reliable estimation of spatio-temporal trends in population-level HIV incidence is becoming an increasingly critical component of HIV prevention policy-making. However, direct measurement is nearly impossible. Current, widely used models infer incidence from survey and surveillance seroprevalence data, but they require unrealistic assumptions about spatial independence across spatial units. In thi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.01590v1-abstract-full').style.display = 'inline'; document.getElementById('1912.01590v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.01590v1-abstract-full" style="display: none;"> Reliable estimation of spatio-temporal trends in population-level HIV incidence is becoming an increasingly critical component of HIV prevention policy-making. However, direct measurement is nearly impossible. Current, widely used models infer incidence from survey and surveillance seroprevalence data, but they require unrealistic assumptions about spatial independence across spatial units. In this study, we present an epidemic model of HIV that explicitly simulates the spatial dynamics of HIV over many small, interacting areal units. By integrating all available population-level data, we are able to infer not only spatio-temporally varying incidence, but also ART initiation rates and patient counts. Our study illustrates the feasibility of applying compartmental models to larger inferential problems than those to which they are typically applied, as well as the value of data fusion approaches to infectious disease modeling. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.01590v1-abstract-full').style.display = 'none'; document.getElementById('1912.01590v1-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> 3 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </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, 9 figures, submitted to Epidemics 7</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.09230">arXiv:1906.09230</a> <span> [<a href="https://arxiv.org/pdf/1906.09230">pdf</a>, <a href="https://arxiv.org/format/1906.09230">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Modeling and Forecasting Art Movements with CGANs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Lisi%2C+E">Edoardo Lisi</a>, <a href="/search/?searchtype=author&query=Malekzadeh%2C+M">Mohammad Malekzadeh</a>, <a href="/search/?searchtype=author&query=Haddadi%2C+H">Hamed Haddadi</a>, <a href="/search/?searchtype=author&query=Lau%2C+F+D">F. Din-Houn Lau</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="1906.09230v2-abstract-short" style="display: inline;"> Conditional Generative Adversarial Networks~(CGAN) are a recent and popular method for generating samples from a probability distribution conditioned on latent information. The latent information often comes in the form of a discrete label from a small set. We propose a novel method for training CGANs which allows us to condition on a sequence of continuous latent distributions… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.09230v2-abstract-full').style.display = 'inline'; document.getElementById('1906.09230v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.09230v2-abstract-full" style="display: none;"> Conditional Generative Adversarial Networks~(CGAN) are a recent and popular method for generating samples from a probability distribution conditioned on latent information. The latent information often comes in the form of a discrete label from a small set. We propose a novel method for training CGANs which allows us to condition on a sequence of continuous latent distributions $f^{(1)}, \ldots, f^{(K)}$. This training allows CGANs to generate samples from a sequence of distributions. We apply our method to paintings from a sequence of artistic movements, where each movement is considered to be its own distribution. Exploiting the temporal aspect of the data, a vector autoregressive (VAR) model is fitted to the means of the latent distributions that we learn, and used for one-step-ahead forecasting, to predict the latent distribution of a future art movement $f^{(K+1)}$. Realisations from this distribution can be used by the CGAN to generate "future" paintings. In experiments, this novel methodology generates accurate predictions of the evolution of art. The training set consists of a large dataset of past paintings. While there is no agreement on exactly what current art period we find ourselves in, we test on plausible candidate sets of present art, and show that the mean distance to our predictions is small. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.09230v2-abstract-full').style.display = 'none'; document.getElementById('1906.09230v2-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> 18 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </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">15 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Royal Society Open Science, 2020 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.09839">arXiv:1901.09839</a> <span> [<a href="https://arxiv.org/pdf/1901.09839">pdf</a>, <a href="https://arxiv.org/format/1901.09839">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Interpreting Deep Neural Networks Through Variable Importance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ish-Horowicz%2C+J">Jonathan Ish-Horowicz</a>, <a href="/search/?searchtype=author&query=Udwin%2C+D">Dana Udwin</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Filippi%2C+S">Sarah Filippi</a>, <a href="/search/?searchtype=author&query=Crawford%2C+L">Lorin Crawford</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="1901.09839v3-abstract-short" style="display: inline;"> While the success of deep neural networks (DNNs) is well-established across a variety of domains, our ability to explain and interpret these methods is limited. Unlike previously proposed local methods which try to explain particular classification decisions, we focus on global interpretability and ask a universally applicable question: given a trained model, which features are the most important?… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.09839v3-abstract-full').style.display = 'inline'; document.getElementById('1901.09839v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.09839v3-abstract-full" style="display: none;"> While the success of deep neural networks (DNNs) is well-established across a variety of domains, our ability to explain and interpret these methods is limited. Unlike previously proposed local methods which try to explain particular classification decisions, we focus on global interpretability and ask a universally applicable question: given a trained model, which features are the most important? In the context of neural networks, a feature is rarely important on its own, so our strategy is specifically designed to leverage partial covariance structures and incorporate variable dependence into feature ranking. Our methodological contributions in this paper are two-fold. First, we propose an effect size analogue for DNNs that is appropriate for applications with highly collinear predictors (ubiquitous in computer vision). Second, we extend the recently proposed "RelATive cEntrality" (RATE) measure (Crawford et al., 2019) to the Bayesian deep learning setting. RATE applies an information theoretic criterion to the posterior distribution of effect sizes to assess feature significance. We apply our framework to three broad application areas: computer vision, natural language processing, and social science. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.09839v3-abstract-full').style.display = 'none'; document.getElementById('1901.09839v3-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 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1805.10205">arXiv:1805.10205</a> <span> [<a href="https://arxiv.org/pdf/1805.10205">pdf</a>, <a href="https://arxiv.org/format/1805.10205">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</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/10.1145/3219819.3219853">10.1145/3219819.3219853 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multimodal Sentiment Analysis To Explore the Structure of Emotions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Hu%2C+A">Anthony Hu</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="1805.10205v1-abstract-short" style="display: inline;"> We propose a novel approach to multimodal sentiment analysis using deep neural networks combining visual analysis and natural language processing. Our goal is different than the standard sentiment analysis goal of predicting whether a sentence expresses positive or negative sentiment; instead, we aim to infer the latent emotional state of the user. Thus, we focus on predicting the emotion word tag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.10205v1-abstract-full').style.display = 'inline'; document.getElementById('1805.10205v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1805.10205v1-abstract-full" style="display: none;"> We propose a novel approach to multimodal sentiment analysis using deep neural networks combining visual analysis and natural language processing. Our goal is different than the standard sentiment analysis goal of predicting whether a sentence expresses positive or negative sentiment; instead, we aim to infer the latent emotional state of the user. Thus, we focus on predicting the emotion word tags attached by users to their Tumblr posts, treating these as "self-reported emotions." We demonstrate that our multimodal model combining both text and image features outperforms separate models based solely on either images or text. Our model's results are interpretable, automatically yielding sensible word lists associated with emotions. We explore the structure of emotions implied by our model and compare it to what has been posited in the psychology literature, and validate our model on a set of images that have been used in psychology studies. Finally, our work also provides a useful tool for the growing academic study of images - both photographs and memes - on social networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.10205v1-abstract-full').style.display = 'none'; document.getElementById('1805.10205v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Accepted as a conference paper at KDD 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/1805.08463">arXiv:1805.08463</a> <span> [<a href="https://arxiv.org/pdf/1805.08463">pdf</a>, <a href="https://arxiv.org/format/1805.08463">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Variational Learning on Aggregate Outputs with Gaussian Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Law%2C+H+C+L">Ho Chung Leon Law</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a>, <a href="/search/?searchtype=author&query=Cameron%2C+E">Ewan Cameron</a>, <a href="/search/?searchtype=author&query=Lucas%2C+T+C">Tim CD Lucas</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Battle%2C+K">Katherine Battle</a>, <a href="/search/?searchtype=author&query=Fukumizu%2C+K">Kenji Fukumizu</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="1805.08463v1-abstract-short" style="display: inline;"> While a typical supervised learning framework assumes that the inputs and the outputs are measured at the same levels of granularity, many applications, including global mapping of disease, only have access to outputs at a much coarser level than that of the inputs. Aggregation of outputs makes generalization to new inputs much more difficult. We consider an approach to this problem based on varia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.08463v1-abstract-full').style.display = 'inline'; document.getElementById('1805.08463v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1805.08463v1-abstract-full" style="display: none;"> While a typical supervised learning framework assumes that the inputs and the outputs are measured at the same levels of granularity, many applications, including global mapping of disease, only have access to outputs at a much coarser level than that of the inputs. Aggregation of outputs makes generalization to new inputs much more difficult. We consider an approach to this problem based on variational learning with a model of output aggregation and Gaussian processes, where aggregation leads to intractability of the standard evidence lower bounds. We propose new bounds and tractable approximations, leading to improved prediction accuracy and scalability to large datasets, while explicitly taking uncertainty into account. We develop a framework which extends to several types of likelihoods, including the Poisson model for aggregated count data. We apply our framework to a challenging and important problem, the fine-scale spatial modelling of malaria incidence, with over 1 million observations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.08463v1-abstract-full').style.display = 'none'; document.getElementById('1805.08463v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1801.07318">arXiv:1801.07318</a> <span> [<a href="https://arxiv.org/pdf/1801.07318">pdf</a>, <a href="https://arxiv.org/format/1801.07318">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Variable Prioritization in Nonlinear Black Box Methods: A Genetic Association Case Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Crawford%2C+L">Lorin Crawford</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S+R">Seth R. Flaxman</a>, <a href="/search/?searchtype=author&query=Runcie%2C+D+E">Daniel E. Runcie</a>, <a href="/search/?searchtype=author&query=West%2C+M">Mike West</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="1801.07318v3-abstract-short" style="display: inline;"> The central aim in this paper is to address variable selection questions in nonlinear and nonparametric regression. Motivated by statistical genetics, where nonlinear interactions are of particular interest, we introduce a novel and interpretable way to summarize the relative importance of predictor variables. Methodologically, we develop the "RelATive cEntrality" (RATE) measure to prioritize cand… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1801.07318v3-abstract-full').style.display = 'inline'; document.getElementById('1801.07318v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1801.07318v3-abstract-full" style="display: none;"> The central aim in this paper is to address variable selection questions in nonlinear and nonparametric regression. Motivated by statistical genetics, where nonlinear interactions are of particular interest, we introduce a novel and interpretable way to summarize the relative importance of predictor variables. Methodologically, we develop the "RelATive cEntrality" (RATE) measure to prioritize candidate genetic variants that are not just marginally important, but whose associations also stem from significant covarying relationships with other variants in the data. We illustrate RATE through Bayesian Gaussian process regression, but the methodological innovations apply to other "black box" methods. It is known that nonlinear models often exhibit greater predictive accuracy than linear models, particularly for phenotypes generated by complex genetic architectures. With detailed simulations and two real data association mapping studies, we show that applying RATE enables an explanation for this improved performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1801.07318v3-abstract-full').style.display = 'none'; document.getElementById('1801.07318v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 August, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 January, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">28 pages, 5 figures, 1 tables; Supplementary Material</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1801.02858">arXiv:1801.02858</a> <span> [<a href="https://arxiv.org/pdf/1801.02858">pdf</a>, <a href="https://arxiv.org/format/1801.02858">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Scalable high-resolution forecasting of sparse spatiotemporal events with kernel methods: a winning solution to the NIJ "Real-Time Crime Forecasting Challenge" </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Chirico%2C+M">Michael Chirico</a>, <a href="/search/?searchtype=author&query=Pereira%2C+P">Pau Pereira</a>, <a href="/search/?searchtype=author&query=Loeffler%2C+C">Charles Loeffler</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="1801.02858v4-abstract-short" style="display: inline;"> We propose a generic spatiotemporal event forecasting method, which we developed for the National Institute of Justice's (NIJ) Real-Time Crime Forecasting Challenge. Our method is a spatiotemporal forecasting model combining scalable randomized Reproducing Kernel Hilbert Space (RKHS) methods for approximating Gaussian processes with autoregressive smoothing kernels in a regularized supervised lear… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1801.02858v4-abstract-full').style.display = 'inline'; document.getElementById('1801.02858v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1801.02858v4-abstract-full" style="display: none;"> We propose a generic spatiotemporal event forecasting method, which we developed for the National Institute of Justice's (NIJ) Real-Time Crime Forecasting Challenge. Our method is a spatiotemporal forecasting model combining scalable randomized Reproducing Kernel Hilbert Space (RKHS) methods for approximating Gaussian processes with autoregressive smoothing kernels in a regularized supervised learning framework. While the smoothing kernels capture the two main approaches in current use in the field of crime forecasting, kernel density estimation (KDE) and self-exciting point process (SEPP) models, the RKHS component of the model can be understood as an approximation to the popular log-Gaussian Cox Process model. For inference, we discretize the spatiotemporal point pattern and learn a log-intensity function using the Poisson likelihood and highly efficient gradient-based optimization methods. Model hyperparameters including quality of RKHS approximation, spatial and temporal kernel lengthscales, number of autoregressive lags, bandwidths for smoothing kernels, as well as cell shape, size, and rotation, were learned using crossvalidation. Resulting predictions significantly exceeded baseline KDE estimates and SEPP models for sparse events. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1801.02858v4-abstract-full').style.display = 'none'; document.getElementById('1801.02858v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 January, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1711.05615">arXiv:1711.05615</a> <span> [<a href="https://arxiv.org/pdf/1711.05615">pdf</a>, <a href="https://arxiv.org/format/1711.05615">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Ton%2C+J">Jean-Francois Ton</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a>, <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</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="1711.05615v1-abstract-short" style="display: inline;"> The use of covariance kernels is ubiquitous in the field of spatial statistics. Kernels allow data to be mapped into high-dimensional feature spaces and can thus extend simple linear additive methods to nonlinear methods with higher order interactions. However, until recently, there has been a strong reliance on a limited class of stationary kernels such as the Matern or squared exponential, limit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.05615v1-abstract-full').style.display = 'inline'; document.getElementById('1711.05615v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1711.05615v1-abstract-full" style="display: none;"> The use of covariance kernels is ubiquitous in the field of spatial statistics. Kernels allow data to be mapped into high-dimensional feature spaces and can thus extend simple linear additive methods to nonlinear methods with higher order interactions. However, until recently, there has been a strong reliance on a limited class of stationary kernels such as the Matern or squared exponential, limiting the expressiveness of these modelling approaches. Recent machine learning research has focused on spectral representations to model arbitrary stationary kernels and introduced more general representations that include classes of nonstationary kernels. In this paper, we exploit the connections between Fourier feature representations, Gaussian processes and neural networks to generalise previous approaches and develop a simple and efficient framework to learn arbitrarily complex nonstationary kernel functions directly from the data, while taking care to avoid overfitting using state-of-the-art methods from deep learning. We highlight the very broad array of kernel classes that could be created within this framework. We apply this to a time series dataset and a remote sensing problem involving land surface temperature in Eastern Africa. We show that without increasing the computational or storage complexity, nonstationary kernels can be used to improve generalisation performance and provide more interpretable results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.05615v1-abstract-full').style.display = 'none'; document.getElementById('1711.05615v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">under submission to Spatial Statistics Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1705.04293">arXiv:1705.04293</a> <span> [<a href="https://arxiv.org/pdf/1705.04293">pdf</a>, <a href="https://arxiv.org/format/1705.04293">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Bayesian Approaches to Distribution Regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Law%2C+H+C+L">Ho Chung Leon Law</a>, <a href="/search/?searchtype=author&query=Sutherland%2C+D+J">Danica J. Sutherland</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="1705.04293v4-abstract-short" style="display: inline;"> Distribution regression has recently attracted much interest as a generic solution to the problem of supervised learning where labels are available at the group level, rather than at the individual level. Current approaches, however, do not propagate the uncertainty in observations due to sampling variability in the groups. This effectively assumes that small and large groups are estimated equally… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1705.04293v4-abstract-full').style.display = 'inline'; document.getElementById('1705.04293v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1705.04293v4-abstract-full" style="display: none;"> Distribution regression has recently attracted much interest as a generic solution to the problem of supervised learning where labels are available at the group level, rather than at the individual level. Current approaches, however, do not propagate the uncertainty in observations due to sampling variability in the groups. This effectively assumes that small and large groups are estimated equally well, and should have equal weight in the final regression. We account for this uncertainty with a Bayesian distribution regression formalism, improving the robustness and performance of the model when group sizes vary. We frame our models in a neural network style, allowing for simple MAP inference using backpropagation to learn the parameters, as well as MCMC-based inference which can fully propagate uncertainty. We demonstrate our approach on illustrative toy datasets, as well as on a challenging problem of predicting age from images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1705.04293v4-abstract-full').style.display = 'none'; document.getElementById('1705.04293v4-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> 14 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 May, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (AISTATS 2018), PMLR 84:1167-1176 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1702.07007">arXiv:1702.07007</a> <span> [<a href="https://arxiv.org/pdf/1702.07007">pdf</a>, <a href="https://arxiv.org/format/1702.07007">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Atmospheric and Oceanic Physics">physics.ao-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</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/10.1126/sciadv.aau4996">10.1126/sciadv.aau4996 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Detecting causal associations in large nonlinear time series datasets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Runge%2C+J">Jakob Runge</a>, <a href="/search/?searchtype=author&query=Nowack%2C+P">Peer Nowack</a>, <a href="/search/?searchtype=author&query=Kretschmer%2C+M">Marlene Kretschmer</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</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="1702.07007v2-abstract-short" style="display: inline;"> Identifying causal relationships from observational time series data is a key problem in disciplines such as climate science or neuroscience, where experiments are often not possible. Data-driven causal inference is challenging since datasets are often high-dimensional and nonlinear with limited sample sizes. Here we introduce a novel method that flexibly combines linear or nonlinear conditional i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.07007v2-abstract-full').style.display = 'inline'; document.getElementById('1702.07007v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1702.07007v2-abstract-full" style="display: none;"> Identifying causal relationships from observational time series data is a key problem in disciplines such as climate science or neuroscience, where experiments are often not possible. Data-driven causal inference is challenging since datasets are often high-dimensional and nonlinear with limited sample sizes. Here we introduce a novel method that flexibly combines linear or nonlinear conditional independence tests with a causal discovery algorithm that allows to reconstruct causal networks from large-scale time series datasets. We validate the method on a well-established climatic teleconnection connecting the tropical Pacific with extra-tropical temperatures and using large-scale synthetic datasets mimicking the typical properties of real data. The experiments demonstrate that our method outperforms alternative techniques in detection power from small to large-scale datasets and opens up entirely new possibilities to discover causal networks from time series across a range of research fields. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.07007v2-abstract-full').style.display = 'none'; document.getElementById('1702.07007v2-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 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 February, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2017. </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">46 pages, 19 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Science Advances Vol. 5, no. 11, eaau4996 (2019) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1612.03278">arXiv:1612.03278</a> <span> [<a href="https://arxiv.org/pdf/1612.03278">pdf</a>, <a href="https://arxiv.org/format/1612.03278">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Improved prediction accuracy for disease risk mapping using Gaussian Process stacked generalisation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Bhatt%2C+S">Samir Bhatt</a>, <a href="/search/?searchtype=author&query=Cameron%2C+E">Ewan Cameron</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S+R">Seth R Flaxman</a>, <a href="/search/?searchtype=author&query=Weiss%2C+D+J">Daniel J Weiss</a>, <a href="/search/?searchtype=author&query=Smith%2C+D+L">David L Smith</a>, <a href="/search/?searchtype=author&query=Gething%2C+P+W">Peter W Gething</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="1612.03278v1-abstract-short" style="display: inline;"> Maps of infectious disease---charting spatial variations in the force of infection, degree of endemicity, and the burden on human health---provide an essential evidence base to support planning towards global health targets. Contemporary disease mapping efforts have embraced statistical modelling approaches to properly acknowledge uncertainties in both the available measurements and their spatial… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1612.03278v1-abstract-full').style.display = 'inline'; document.getElementById('1612.03278v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1612.03278v1-abstract-full" style="display: none;"> Maps of infectious disease---charting spatial variations in the force of infection, degree of endemicity, and the burden on human health---provide an essential evidence base to support planning towards global health targets. Contemporary disease mapping efforts have embraced statistical modelling approaches to properly acknowledge uncertainties in both the available measurements and their spatial interpolation. The most common such approach is that of Gaussian process regression, a mathematical framework comprised of two components: a mean function harnessing the predictive power of multiple independent variables, and a covariance function yielding spatio-temporal shrinkage against residual variation from the mean. Though many techniques have been developed to improve the flexibility and fitting of the covariance function, models for the mean function have typically been restricted to simple linear terms. For infectious diseases, known to be driven by complex interactions between environmental and socio-economic factors, improved modelling of the mean function can greatly boost predictive power. Here we present an ensemble approach based on stacked generalisation that allows for multiple, non-linear algorithmic mean functions to be jointly embedded within the Gaussian process framework. We apply this method to mapping Plasmodium falciparum prevalence data in Sub-Saharan Africa and show that the generalised ensemble approach markedly out-performs any individual method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1612.03278v1-abstract-full').style.display = 'none'; document.getElementById('1612.03278v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 December, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">Under Submission</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1611.06713">arXiv:1611.06713</a> <span> [<a href="https://arxiv.org/pdf/1611.06713">pdf</a>, <a href="https://arxiv.org/format/1611.06713">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> </div> </div> <p class="title is-5 mathjax"> Is Gun Violence Contagious? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Loeffler%2C+C">Charles Loeffler</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="1611.06713v1-abstract-short" style="display: inline;"> Existing theories of gun violence predict stable spatial concentrations and contagious diffusion of gun violence into surrounding areas. Recent empirical studies have reported confirmatory evidence of such spatiotemporal diffusion of gun violence. However, existing tests cannot readily distinguish spatiotemporal clustering from spatiotemporal diffusion. This leaves as an open question whether gun… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1611.06713v1-abstract-full').style.display = 'inline'; document.getElementById('1611.06713v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1611.06713v1-abstract-full" style="display: none;"> Existing theories of gun violence predict stable spatial concentrations and contagious diffusion of gun violence into surrounding areas. Recent empirical studies have reported confirmatory evidence of such spatiotemporal diffusion of gun violence. However, existing tests cannot readily distinguish spatiotemporal clustering from spatiotemporal diffusion. This leaves as an open question whether gun violence actually is contagious or merely clusters in space and time. Compounding this problem, gun violence is subject to considerable measurement error with many nonfatal shootings going unreported to police. Using point process data from an acoustical gunshot locator system and a combination of Bayesian spatiotemporal point process modeling and space/time interaction tests, this paper demonstrates that contemporary urban gun violence does diffuse, but only slightly, suggesting that a disease model for infectious spread of gun violence is a poor fit for the geographically stable and temporally stochastic process observed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1611.06713v1-abstract-full').style.display = 'none'; document.getElementById('1611.06713v1-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, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2016. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1611.03787">arXiv:1611.03787</a> <span> [<a href="https://arxiv.org/pdf/1611.03787">pdf</a>, <a href="https://arxiv.org/format/1611.03787">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sutherland%2C+D+J">Danica J. Sutherland</a>, <a href="/search/?searchtype=author&query=Wang%2C+Y">Yu-Xiang Wang</a>, <a href="/search/?searchtype=author&query=Teh%2C+Y+W">Yee Whye Teh</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="1611.03787v2-abstract-short" style="display: inline;"> We combine fine-grained spatially referenced census data with the vote outcomes from the 2016 US presidential election. Using this dataset, we perform ecological inference using distribution regression (Flaxman et al, KDD 2015) with a multinomial-logit regression so as to model the vote outcome Trump, Clinton, Other / Didn't vote as a function of demographic and socioeconomic features. Ecological… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1611.03787v2-abstract-full').style.display = 'inline'; document.getElementById('1611.03787v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1611.03787v2-abstract-full" style="display: none;"> We combine fine-grained spatially referenced census data with the vote outcomes from the 2016 US presidential election. Using this dataset, we perform ecological inference using distribution regression (Flaxman et al, KDD 2015) with a multinomial-logit regression so as to model the vote outcome Trump, Clinton, Other / Didn't vote as a function of demographic and socioeconomic features. Ecological inference allows us to estimate "exit poll" style results like what was Trump's support among white women, but for entirely novel categories. We also perform exploratory data analysis to understand which census variables are predictive of voting for Trump, voting for Clinton, or not voting for either. All of our methods are implemented in Python and R, and are available online for replication. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1611.03787v2-abstract-full').style.display = 'none'; document.getElementById('1611.03787v2-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> 14 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 November, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2016. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1610.08623">arXiv:1610.08623</a> <span> [<a href="https://arxiv.org/pdf/1610.08623">pdf</a>, <a href="https://arxiv.org/format/1610.08623">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Poisson intensity estimation with reproducing kernels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Teh%2C+Y+W">Yee Whye Teh</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</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="1610.08623v3-abstract-short" style="display: inline;"> Despite the fundamental nature of the inhomogeneous Poisson process in the theory and application of stochastic processes, and its attractive generalizations (e.g. Cox process), few tractable nonparametric modeling approaches of intensity functions exist, especially when observed points lie in a high-dimensional space. In this paper we develop a new, computationally tractable Reproducing Kernel Hi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1610.08623v3-abstract-full').style.display = 'inline'; document.getElementById('1610.08623v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1610.08623v3-abstract-full" style="display: none;"> Despite the fundamental nature of the inhomogeneous Poisson process in the theory and application of stochastic processes, and its attractive generalizations (e.g. Cox process), few tractable nonparametric modeling approaches of intensity functions exist, especially when observed points lie in a high-dimensional space. In this paper we develop a new, computationally tractable Reproducing Kernel Hilbert Space (RKHS) formulation for the inhomogeneous Poisson process. We model the square root of the intensity as an RKHS function. Whereas RKHS models used in supervised learning rely on the so-called representer theorem, the form of the inhomogeneous Poisson process likelihood means that the representer theorem does not apply. However, we prove that the representer theorem does hold in an appropriately transformed RKHS, guaranteeing that the optimization of the penalized likelihood can be cast as a tractable finite-dimensional problem. The resulting approach is simple to implement, and readily scales to high dimensions and large-scale datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1610.08623v3-abstract-full').style.display = 'none'; document.getElementById('1610.08623v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 June, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 October, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">AISTATS 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1606.08813">arXiv:1606.08813</a> <span> [<a href="https://arxiv.org/pdf/1606.08813">pdf</a>, <a href="https://arxiv.org/format/1606.08813">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</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/10.1609/aimag.v38i3.2741">10.1609/aimag.v38i3.2741 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> European Union regulations on algorithmic decision-making and a "right to explanation" </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Goodman%2C+B">Bryce Goodman</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</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="1606.08813v3-abstract-short" style="display: inline;"> We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user-level predictors) which "significantly affect" users. The law will also effecti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1606.08813v3-abstract-full').style.display = 'inline'; document.getElementById('1606.08813v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1606.08813v3-abstract-full" style="display: none;"> We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user-level predictors) which "significantly affect" users. The law will also effectively create a "right to explanation," whereby a user can ask for an explanation of an algorithmic decision that was made about them. We argue that while this law will pose large challenges for industry, it highlights opportunities for computer scientists to take the lead in designing algorithms and evaluation frameworks which avoid discrimination and enable explanation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1606.08813v3-abstract-full').style.display = 'none'; document.getElementById('1606.08813v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 August, 2016; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">presented at 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> AI Magazine, Vol 38, No 3, 2017 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1605.07025">arXiv:1605.07025</a> <span> [<a href="https://arxiv.org/pdf/1605.07025">pdf</a>, <a href="https://arxiv.org/format/1605.07025">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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"> Collaborative Filtering with Side Information: a Gaussian Process Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Kim%2C+H">Hyunjik Kim</a>, <a href="/search/?searchtype=author&query=Lu%2C+X">Xiaoyu Lu</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Teh%2C+Y+W">Yee Whye Teh</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="1605.07025v3-abstract-short" style="display: inline;"> We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression. Driven by the idea of using the kernel to explicitly model user-item similarities, we formulate the GP in a way that allows the incorporation of low-rank matrix factorisation, arriving at our model, the Tucker Gaussian Process (TGP). Consequently, TGP generalises class… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1605.07025v3-abstract-full').style.display = 'inline'; document.getElementById('1605.07025v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1605.07025v3-abstract-full" style="display: none;"> We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression. Driven by the idea of using the kernel to explicitly model user-item similarities, we formulate the GP in a way that allows the incorporation of low-rank matrix factorisation, arriving at our model, the Tucker Gaussian Process (TGP). Consequently, TGP generalises classical Bayesian matrix factorisation models, and goes beyond them to give a natural and elegant method for incorporating side information, giving enhanced predictive performance for CF problems. Moreover we show that it is a novel model for regression, especially well-suited to grid-structured data and problems where the dependence on covariates is close to being separable. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1605.07025v3-abstract-full').style.display = 'none'; document.getElementById('1605.07025v3-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 June, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 May, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2016. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1603.02160">arXiv:1603.02160</a> <span> [<a href="https://arxiv.org/pdf/1603.02160">pdf</a>, <a href="https://arxiv.org/format/1603.02160">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Bayesian Learning of Kernel Embeddings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Sejdinovic%2C+D">Dino Sejdinovic</a>, <a href="/search/?searchtype=author&query=Cunningham%2C+J+P">John P. Cunningham</a>, <a href="/search/?searchtype=author&query=Filippi%2C+S">Sarah Filippi</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="1603.02160v2-abstract-short" style="display: inline;"> Kernel methods are one of the mainstays of machine learning, but the problem of kernel learning remains challenging, with only a few heuristics and very little theory. This is of particular importance in methods based on estimation of kernel mean embeddings of probability measures. For characteristic kernels, which include most commonly used ones, the kernel mean embedding uniquely determines its… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1603.02160v2-abstract-full').style.display = 'inline'; document.getElementById('1603.02160v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1603.02160v2-abstract-full" style="display: none;"> Kernel methods are one of the mainstays of machine learning, but the problem of kernel learning remains challenging, with only a few heuristics and very little theory. This is of particular importance in methods based on estimation of kernel mean embeddings of probability measures. For characteristic kernels, which include most commonly used ones, the kernel mean embedding uniquely determines its probability measure, so it can be used to design a powerful statistical testing framework, which includes nonparametric two-sample and independence tests. In practice, however, the performance of these tests can be very sensitive to the choice of kernel and its lengthscale parameters. To address this central issue, we propose a new probabilistic model for kernel mean embeddings, the Bayesian Kernel Embedding model, combining a Gaussian process prior over the Reproducing Kernel Hilbert Space containing the mean embedding with a conjugate likelihood function, thus yielding a closed form posterior over the mean embedding. The posterior mean of our model is closely related to recently proposed shrinkage estimators for kernel mean embeddings, while the posterior uncertainty is a new, interesting feature with various possible applications. Critically for the purposes of kernel learning, our model gives a simple, closed form marginal pseudolikelihood of the observed data given the kernel hyperparameters. This marginal pseudolikelihood can either be optimized to inform the hyperparameter choice or fully Bayesian inference can be used. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1603.02160v2-abstract-full').style.display = 'none'; document.getElementById('1603.02160v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 June, 2016; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 March, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">Conference paper appearing in UAI 2016, including Appendix</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1511.04408">arXiv:1511.04408</a> <span> [<a href="https://arxiv.org/pdf/1511.04408">pdf</a>, <a href="https://arxiv.org/format/1511.04408">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Scalable Gaussian Processes for Characterizing Multidimensional Change Surfaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/?searchtype=author&query=Herlands%2C+W">William Herlands</a>, <a href="/search/?searchtype=author&query=Wilson%2C+A">Andrew Wilson</a>, <a href="/search/?searchtype=author&query=Nickisch%2C+H">Hannes Nickisch</a>, <a href="/search/?searchtype=author&query=Flaxman%2C+S">Seth Flaxman</a>, <a href="/search/?searchtype=author&query=Neill%2C+D">Daniel Neill</a>, <a href="/search/?searchtype=author&query=van+Panhuis%2C+W">Wilbert van Panhuis</a>, <a href="/search/?searchtype=author&query=Xing%2C+E">Eric Xing</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="1511.04408v1-abstract-short" style="display: inline;"> We present a scalable Gaussian process model for identifying and characterizing smooth multidimensional changepoints, and automatically learning changes in expressive covariance structure. We use Random Kitchen Sink features to flexibly define a change surface in combination with expressive spectral mixture kernels to capture the complex statistical structure. Finally, through the use of novel met… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1511.04408v1-abstract-full').style.display = 'inline'; document.getElementById('1511.04408v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1511.04408v1-abstract-full" style="display: none;"> We present a scalable Gaussian process model for identifying and characterizing smooth multidimensional changepoints, and automatically learning changes in expressive covariance structure. We use Random Kitchen Sink features to flexibly define a change surface in combination with expressive spectral mixture kernels to capture the complex statistical structure. Finally, through the use of novel methods for additive non-separable kernels, we can scale the model to large datasets. We demonstrate the model on numerical and real world data, including a large spatio-temporal disease dataset where we identify previously unknown heterogeneous changes in space and time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1511.04408v1-abstract-full').style.display = 'none'; document.getElementById('1511.04408v1-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 November, 2015; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2015. </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">18 pages, 8 figures</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Flaxman%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Flaxman%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Flaxman%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository