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 70 results for author: <span class="mathjax">Shankar, 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/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Shankar%2C+S">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Shankar, 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=Shankar%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="Shankar, 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=Shankar%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Shankar%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Shankar%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/2410.12189">arXiv:2410.12189</a> <span> [<a href="https://arxiv.org/pdf/2410.12189">pdf</a>, <a href="https://arxiv.org/format/2410.12189">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+E">Eugene Wu</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="2410.12189v1-abstract-short" style="display: inline;"> Analyzing unstructured data, such as complex documents, has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered unstructured data processing. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving acc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12189v1-abstract-full').style.display = 'inline'; document.getElementById('2410.12189v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12189v1-abstract-full" style="display: none;"> Analyzing unstructured data, such as complex documents, has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered unstructured data processing. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving accuracy, executing most operations as-is. This is problematic for complex tasks and data, where LLM outputs for user-defined operations are often inaccurate, even with optimized prompts. We present DocETL, a system that optimizes complex document processing pipelines, while accounting for LLM shortcomings. DocETL offers a declarative interface for users to define such pipelines and uses an agent-based framework to automatically optimize them, leveraging novel agent-based rewrites (that we call {\em rewrite directives}) and an optimization and evaluation framework that we introduce. We introduce {\em (i)} logical rewriting of pipelines, tailored for LLM-based tasks, {\em (ii)} an agent-guided plan evaluation mechanism that synthesizes and orchestrates task-specific validation prompts, and {\em (iii)} an optimization algorithm that efficiently finds promising plans, considering the time constraints of LLM-based plan generation and evaluation. Our evaluation on three different unstructured document analysis tasks demonstrates that DocETL finds plans with outputs that are $1.34$ to $4.6\times$ higher quality (e.g., more accurate, comprehensive) than well-engineered baselines, addressing a critical gap in existing declarative frameworks for unstructured data analysis. DocETL is open-source at \ttt{docetl.org}, and as of October 2024, has amassed over 800 GitHub Stars, with users spanning a variety of domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12189v1-abstract-full').style.display = 'none'; document.getElementById('2410.12189v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">21 pages, 7 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/2407.21783">arXiv:2407.21783</a> <span> [<a href="https://arxiv.org/pdf/2407.21783">pdf</a>, <a href="https://arxiv.org/format/2407.21783">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> The Llama 3 Herd of Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Grattafiori%2C+A">Aaron Grattafiori</a>, <a href="/search/cs?searchtype=author&query=Dubey%2C+A">Abhimanyu Dubey</a>, <a href="/search/cs?searchtype=author&query=Jauhri%2C+A">Abhinav Jauhri</a>, <a href="/search/cs?searchtype=author&query=Pandey%2C+A">Abhinav Pandey</a>, <a href="/search/cs?searchtype=author&query=Kadian%2C+A">Abhishek Kadian</a>, <a href="/search/cs?searchtype=author&query=Al-Dahle%2C+A">Ahmad Al-Dahle</a>, <a href="/search/cs?searchtype=author&query=Letman%2C+A">Aiesha Letman</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+A">Akhil Mathur</a>, <a href="/search/cs?searchtype=author&query=Schelten%2C+A">Alan Schelten</a>, <a href="/search/cs?searchtype=author&query=Vaughan%2C+A">Alex Vaughan</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+A">Amy Yang</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+A">Angela Fan</a>, <a href="/search/cs?searchtype=author&query=Goyal%2C+A">Anirudh Goyal</a>, <a href="/search/cs?searchtype=author&query=Hartshorn%2C+A">Anthony Hartshorn</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+A">Aobo Yang</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+A">Archi Mitra</a>, <a href="/search/cs?searchtype=author&query=Sravankumar%2C+A">Archie Sravankumar</a>, <a href="/search/cs?searchtype=author&query=Korenev%2C+A">Artem Korenev</a>, <a href="/search/cs?searchtype=author&query=Hinsvark%2C+A">Arthur Hinsvark</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+A">Arun Rao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A">Aston Zhang</a>, <a href="/search/cs?searchtype=author&query=Rodriguez%2C+A">Aurelien Rodriguez</a>, <a href="/search/cs?searchtype=author&query=Gregerson%2C+A">Austen Gregerson</a>, <a href="/search/cs?searchtype=author&query=Spataru%2C+A">Ava Spataru</a>, <a href="/search/cs?searchtype=author&query=Roziere%2C+B">Baptiste Roziere</a> , et al. (536 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.21783v3-abstract-short" style="display: inline;"> Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21783v3-abstract-full').style.display = 'inline'; document.getElementById('2407.21783v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.21783v3-abstract-full" style="display: none;"> Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21783v3-abstract-full').style.display = 'none'; document.getElementById('2407.21783v3-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.17910">arXiv:2406.17910</a> <span> [<a href="https://arxiv.org/pdf/2406.17910">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Transforming Software Development: Evaluating the Efficiency and Challenges of GitHub Copilot in Real-World Projects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pandey%2C+R">Ruchika Pandey</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+P">Prabhat Singh</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+R">Raymond Wei</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shaila Shankar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.17910v1-abstract-short" style="display: inline;"> Generative AI technologies promise to transform the product development lifecycle. This study evaluates the efficiency gains, areas for improvement, and emerging challenges of using GitHub Copilot, an AI-powered coding assistant. We identified 15 software development tasks and assessed Copilot's benefits through real-world projects on large proprietary code bases. Our findings indicate significant… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17910v1-abstract-full').style.display = 'inline'; document.getElementById('2406.17910v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.17910v1-abstract-full" style="display: none;"> Generative AI technologies promise to transform the product development lifecycle. This study evaluates the efficiency gains, areas for improvement, and emerging challenges of using GitHub Copilot, an AI-powered coding assistant. We identified 15 software development tasks and assessed Copilot's benefits through real-world projects on large proprietary code bases. Our findings indicate significant reductions in developer toil, with up to 50% time saved in code documentation and autocompletion, and 30-40% in repetitive coding tasks, unit test generation, debugging, and pair programming. However, Copilot struggles with complex tasks, large functions, multiple files, and proprietary contexts, particularly with C/C++ code. We project a 33-36% time reduction for coding-related tasks in a cloud-first software development lifecycle. This study aims to quantify productivity improvements, identify underperforming scenarios, examine practical benefits and challenges, investigate performance variations across programming languages, and discuss emerging issues related to code quality, security, and developer experience. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17910v1-abstract-full').style.display = 'none'; document.getElementById('2406.17910v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 8 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/2406.05224">arXiv:2406.05224</a> <span> [<a href="https://arxiv.org/pdf/2406.05224">pdf</a>, <a href="https://arxiv.org/format/2406.05224">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> ON-OFF Neuromorphic ISING Machines using Fowler-Nordheim Annealers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zihao Chen</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+Z">Zhili Xiao</a>, <a href="/search/cs?searchtype=author&query=Akl%2C+M">Mahmoud Akl</a>, <a href="/search/cs?searchtype=author&query=Leugring%2C+J">Johannes Leugring</a>, <a href="/search/cs?searchtype=author&query=Olajide%2C+O">Omowuyi Olajide</a>, <a href="/search/cs?searchtype=author&query=Malik%2C+A">Adil Malik</a>, <a href="/search/cs?searchtype=author&query=Dennler%2C+N">Nik Dennler</a>, <a href="/search/cs?searchtype=author&query=Harper%2C+C">Chad Harper</a>, <a href="/search/cs?searchtype=author&query=Bose%2C+S">Subhankar Bose</a>, <a href="/search/cs?searchtype=author&query=Gonzalez%2C+H+A">Hector A. Gonzalez</a>, <a href="/search/cs?searchtype=author&query=Eshraghian%2C+J">Jason Eshraghian</a>, <a href="/search/cs?searchtype=author&query=Pignari%2C+R">Riccardo Pignari</a>, <a href="/search/cs?searchtype=author&query=Urgese%2C+G">Gianvito Urgese</a>, <a href="/search/cs?searchtype=author&query=Andreou%2C+A+G">Andreas G. Andreou</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sadasivan Shankar</a>, <a href="/search/cs?searchtype=author&query=Mayr%2C+C">Christian Mayr</a>, <a href="/search/cs?searchtype=author&query=Cauwenberghs%2C+G">Gert Cauwenberghs</a>, <a href="/search/cs?searchtype=author&query=Chakrabartty%2C+S">Shantanu Chakrabartty</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.05224v1-abstract-short" style="display: inline;"> We introduce NeuroSA, a neuromorphic architecture specifically designed to ensure asymptotic convergence to the ground state of an Ising problem using an annealing process that is governed by the physics of quantum mechanical tunneling using Fowler-Nordheim (FN). The core component of NeuroSA consists of a pair of asynchronous ON-OFF neurons, which effectively map classical simulated annealing (SA… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05224v1-abstract-full').style.display = 'inline'; document.getElementById('2406.05224v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05224v1-abstract-full" style="display: none;"> We introduce NeuroSA, a neuromorphic architecture specifically designed to ensure asymptotic convergence to the ground state of an Ising problem using an annealing process that is governed by the physics of quantum mechanical tunneling using Fowler-Nordheim (FN). The core component of NeuroSA consists of a pair of asynchronous ON-OFF neurons, which effectively map classical simulated annealing (SA) dynamics onto a network of integrate-and-fire (IF) neurons. The threshold of each ON-OFF neuron pair is adaptively adjusted by an FN annealer which replicates the optimal escape mechanism and convergence of SA, particularly at low temperatures. To validate the effectiveness of our neuromorphic Ising machine, we systematically solved various benchmark MAX-CUT combinatorial optimization problems. Across multiple runs, NeuroSA consistently generates solutions that approach the state-of-the-art level with high accuracy (greater than 99%), and without any graph-specific hyperparameter tuning. For practical illustration, we present results from an implementation of NeuroSA on the SpiNNaker2 platform, highlighting the feasibility of mapping our proposed architecture onto a standard neuromorphic accelerator platform. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05224v1-abstract-full').style.display = 'none'; document.getElementById('2406.05224v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">36 pages, 8 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/2405.04674">arXiv:2405.04674</a> <span> [<a href="https://arxiv.org/pdf/2405.04674">pdf</a>, <a href="https://arxiv.org/format/2405.04674">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Towards Accurate and Efficient Document Analytics with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yiming Lin</a>, <a href="/search/cs?searchtype=author&query=Hulsebos%2C+M">Madelon Hulsebos</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+R">Ruiying Ma</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Zeigham%2C+S">Sepanta Zeigham</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+E">Eugene Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.04674v1-abstract-short" style="display: inline;"> Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support ad-hoc analytical queries on document collections. Moreover, Large Language Models (LLMs) directly applied to the documents themselves, or on portions of documents t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.04674v1-abstract-full').style.display = 'inline'; document.getElementById('2405.04674v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.04674v1-abstract-full" style="display: none;"> Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support ad-hoc analytical queries on document collections. Moreover, Large Language Models (LLMs) directly applied to the documents themselves, or on portions of documents through a process of Retrieval-Augmented Generation (RAG), fail to provide high accuracy query results, and in the LLM-only case, additionally incur high costs. Since many unstructured documents in a collection often follow similar templates that impart a common semantic structure, we introduce ZenDB, a document analytics system that leverages this semantic structure, coupled with LLMs, to answer ad-hoc SQL queries on document collections. ZenDB efficiently extracts semantic hierarchical structures from such templatized documents, and introduces a novel query engine that leverages these structures for accurate and cost-effective query execution. Users can impose a schema on their documents, and query it, all via SQL. Extensive experiments on three real-world document collections demonstrate ZenDB's benefits, achieving up to 30% cost savings compared to LLM-based baselines, while maintaining or improving accuracy, and surpassing RAG-based baselines by up to 61% in precision and 80% in recall, at a marginally higher cost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.04674v1-abstract-full').style.display = 'none'; document.getElementById('2405.04674v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.12272">arXiv:2404.12272</a> <span> [<a href="https://arxiv.org/pdf/2404.12272">pdf</a>, <a href="https://arxiv.org/format/2404.12272">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Zamfirescu-Pereira%2C+J+D">J. D. Zamfirescu-Pereira</a>, <a href="/search/cs?searchtype=author&query=Hartmann%2C+B">Bj枚rn Hartmann</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a>, <a href="/search/cs?searchtype=author&query=Arawjo%2C+I">Ian Arawjo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.12272v1-abstract-short" style="display: inline;"> Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators simply inherit all the problems of the LLMs they evaluate, requiring further human validation. We present a mixed-initiative approach to ``validate the validators'' -- aligning LL… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.12272v1-abstract-full').style.display = 'inline'; document.getElementById('2404.12272v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.12272v1-abstract-full" style="display: none;"> Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators simply inherit all the problems of the LLMs they evaluate, requiring further human validation. We present a mixed-initiative approach to ``validate the validators'' -- aligning LLM-generated evaluation functions (be it prompts or code) with human requirements. Our interface, EvalGen, provides automated assistance to users in generating evaluation criteria and implementing assertions. While generating candidate implementations (Python functions, LLM grader prompts), EvalGen asks humans to grade a subset of LLM outputs; this feedback is used to select implementations that better align with user grades. A qualitative study finds overall support for EvalGen but underscores the subjectivity and iterative process of alignment. In particular, we identify a phenomenon we dub \emph{criteria drift}: users need criteria to grade outputs, but grading outputs helps users define criteria. What is more, some criteria appears \emph{dependent} on the specific LLM outputs observed (rather than independent criteria that can be defined \emph{a priori}), raising serious questions for approaches that assume the independence of evaluation from observation of model outputs. We present our interface and implementation details, a comparison of our algorithm with a baseline approach, and implications for the design of future LLM evaluation assistants. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.12272v1-abstract-full').style.display = 'none'; document.getElementById('2404.12272v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 4 figures, 2 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/2404.10547">arXiv:2404.10547</a> <span> [<a href="https://arxiv.org/pdf/2404.10547">pdf</a>, <a href="https://arxiv.org/format/2404.10547">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"> A/B testing under Interference with Partial Network Information </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+R">Ritwik Sinha</a>, <a href="/search/cs?searchtype=author&query=Chandak%2C+Y">Yash Chandak</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Saayan Mitra</a>, <a href="/search/cs?searchtype=author&query=Fiterau%2C+M">Madalina Fiterau</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.10547v1-abstract-short" style="display: inline;"> A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control the spread of an epidemic. In such settings, the SUTVA assumption for randomized-controlled trials is violated due to network interference, or spill-over effects, as treatments to group A can potentially also affect the c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.10547v1-abstract-full').style.display = 'inline'; document.getElementById('2404.10547v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.10547v1-abstract-full" style="display: none;"> A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control the spread of an epidemic. In such settings, the SUTVA assumption for randomized-controlled trials is violated due to network interference, or spill-over effects, as treatments to group A can potentially also affect the control group B. When the underlying social network is known exactly, prior works have demonstrated how to conduct A/B tests adequately to estimate the global average treatment effect (GATE). However, in practice, it is often impossible to obtain knowledge about the exact underlying network. In this paper, we present UNITE: a novel estimator that relax this assumption and can identify GATE while only relying on knowledge of the superset of neighbors for any subject in the graph. Through theoretical analysis and extensive experiments, we show that the proposed approach performs better in comparison to standard estimators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.10547v1-abstract-full').style.display = 'none'; document.getElementById('2404.10547v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">AISTATS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.16795">arXiv:2403.16795</a> <span> [<a href="https://arxiv.org/pdf/2403.16795">pdf</a>, <a href="https://arxiv.org/format/2403.16795">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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/10.1145/3653697">10.1145/3653697 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> "We Have No Idea How Models will Behave in Production until Production": How Engineers Operationalize Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Garcia%2C+R">Rolando Garcia</a>, <a href="/search/cs?searchtype=author&query=Hellerstein%2C+J+M">Joseph M Hellerstein</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G Parameswaran</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="2403.16795v1-abstract-short" style="display: inline;"> Organizations rely on machine learning engineers (MLEs) to deploy models and maintain ML pipelines in production. Due to models' extensive reliance on fresh data, the operationalization of machine learning, or MLOps, requires MLEs to have proficiency in data science and engineering. When considered holistically, the job seems staggering -- how do MLEs do MLOps, and what are their unaddressed chall… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.16795v1-abstract-full').style.display = 'inline'; document.getElementById('2403.16795v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.16795v1-abstract-full" style="display: none;"> Organizations rely on machine learning engineers (MLEs) to deploy models and maintain ML pipelines in production. Due to models' extensive reliance on fresh data, the operationalization of machine learning, or MLOps, requires MLEs to have proficiency in data science and engineering. When considered holistically, the job seems staggering -- how do MLEs do MLOps, and what are their unaddressed challenges? To address these questions, we conducted semi-structured ethnographic interviews with 18 MLEs working on various applications, including chatbots, autonomous vehicles, and finance. We find that MLEs engage in a workflow of (i) data preparation, (ii) experimentation, (iii) evaluation throughout a multi-staged deployment, and (iv) continual monitoring and response. Throughout this workflow, MLEs collaborate extensively with data scientists, product stakeholders, and one another, supplementing routine verbal exchanges with communication tools ranging from Slack to organization-wide ticketing and reporting systems. We introduce the 3Vs of MLOps: velocity, visibility, and versioning -- three virtues of successful ML deployments that MLEs learn to balance and grow as they mature. Finally, we discuss design implications and opportunities for future work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.16795v1-abstract-full').style.display = 'none'; document.getElementById('2403.16795v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: text overlap with arXiv:2209.09125</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proc. ACM Hum.-Comput. Interact. 8, CSCW1, Article 206 (April 2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.15968">arXiv:2402.15968</a> <span> [<a href="https://arxiv.org/pdf/2402.15968">pdf</a>, <a href="https://arxiv.org/format/2402.15968">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> </div> </div> <p class="title is-5 mathjax"> CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+G">Gauri Gupta</a>, <a href="/search/cs?searchtype=author&query=Kapila%2C+R">Ritvik Kapila</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yichuan Shi</a>, <a href="/search/cs?searchtype=author&query=Dang%2C+A">Alex Dang</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Ehab%2C+M">Mohammed Ehab</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.15968v2-abstract-short" style="display: inline;"> Federated Learning (FL) enables collaborative optimization of machine learning models across decentralized data by aggregating model parameters. Our approach extends this concept by aggregating "knowledge" derived from models, instead of model parameters. We present a novel framework called CoDream, where clients collaboratively optimize randomly initialized data using federated optimization in th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15968v2-abstract-full').style.display = 'inline'; document.getElementById('2402.15968v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.15968v2-abstract-full" style="display: none;"> Federated Learning (FL) enables collaborative optimization of machine learning models across decentralized data by aggregating model parameters. Our approach extends this concept by aggregating "knowledge" derived from models, instead of model parameters. We present a novel framework called CoDream, where clients collaboratively optimize randomly initialized data using federated optimization in the input data space, similar to how randomly initialized model parameters are optimized in FL. Our key insight is that jointly optimizing this data can effectively capture the properties of the global data distribution. Sharing knowledge in data space offers numerous benefits: (1) model-agnostic collaborative learning, i.e., different clients can have different model architectures; (2) communication that is independent of the model size, eliminating scalability concerns with model parameters; (3) compatibility with secure aggregation, thus preserving the privacy benefits of federated learning; (4) allowing of adaptive optimization of knowledge shared for personalized learning. We empirically validate CoDream on standard FL tasks, demonstrating competitive performance despite not sharing model parameters. Our code: https://mitmedialab.github.io/codream.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15968v2-abstract-full').style.display = 'none'; document.getElementById('2402.15968v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 12 figures, 5 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/2401.03038">arXiv:2401.03038</a> <span> [<a href="https://arxiv.org/pdf/2401.03038">pdf</a>, <a href="https://arxiv.org/format/2401.03038">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haotian Li</a>, <a href="/search/cs?searchtype=author&query=Asawa%2C+P">Parth Asawa</a>, <a href="/search/cs?searchtype=author&query=Hulsebos%2C+M">Madelon Hulsebos</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Y">Yiming Lin</a>, <a href="/search/cs?searchtype=author&query=Zamfirescu-Pereira%2C+J+D">J. D. Zamfirescu-Pereira</a>, <a href="/search/cs?searchtype=author&query=Chase%2C+H">Harrison Chase</a>, <a href="/search/cs?searchtype=author&query=Fu-Hinthorn%2C+W">Will Fu-Hinthorn</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+E">Eugene Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.03038v2-abstract-short" style="display: inline;"> Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague LLMs. Acknowledging the inevitability of these errors, we propose {\em data quality assertions} to identify when LLMs may be making mistakes. We present SPADE, a m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03038v2-abstract-full').style.display = 'inline'; document.getElementById('2401.03038v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.03038v2-abstract-full" style="display: none;"> Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague LLMs. Acknowledging the inevitability of these errors, we propose {\em data quality assertions} to identify when LLMs may be making mistakes. We present SPADE, a method for automatically synthesizing data quality assertions that identify bad LLM outputs. We make the observation that developers often identify data quality issues during prototyping prior to deployment, and attempt to address them by adding instructions to the LLM prompt over time. SPADE therefore analyzes histories of prompt versions over time to create candidate assertion functions and then selects a minimal set that fulfills both coverage and accuracy requirements. In testing across nine different real-world LLM pipelines, SPADE efficiently reduces the number of assertions by 14\% and decreases false failures by 21\% when compared to simpler baselines. SPADE has been deployed as an offering within LangSmith, LangChain's LLM pipeline hub, and has been used to generate data quality assertions for over 2000 pipelines across a spectrum of industries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03038v2-abstract-full').style.display = 'none'; document.getElementById('2401.03038v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.02438">arXiv:2312.02438</a> <span> [<a href="https://arxiv.org/pdf/2312.02438">pdf</a>, <a href="https://arxiv.org/format/2312.02438">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"> Adaptive Instrument Design for Indirect Experiments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chandak%2C+Y">Yash Chandak</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Syrgkanis%2C+V">Vasilis Syrgkanis</a>, <a href="/search/cs?searchtype=author&query=Brunskill%2C+E">Emma Brunskill</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="2312.02438v1-abstract-short" style="display: inline;"> Indirect experiments provide a valuable framework for estimating treatment effects in situations where conducting randomized control trials (RCTs) is impractical or unethical. Unlike RCTs, indirect experiments estimate treatment effects by leveraging (conditional) instrumental variables, enabling estimation through encouragement and recommendation rather than strict treatment assignment. However,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.02438v1-abstract-full').style.display = 'inline'; document.getElementById('2312.02438v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.02438v1-abstract-full" style="display: none;"> Indirect experiments provide a valuable framework for estimating treatment effects in situations where conducting randomized control trials (RCTs) is impractical or unethical. Unlike RCTs, indirect experiments estimate treatment effects by leveraging (conditional) instrumental variables, enabling estimation through encouragement and recommendation rather than strict treatment assignment. However, the sample efficiency of such estimators depends not only on the inherent variability in outcomes but also on the varying compliance levels of users with the instrumental variables and the choice of estimator being used, especially when dealing with numerous instrumental variables. While adaptive experiment design has a rich literature for direct experiments, in this paper we take the initial steps towards enhancing sample efficiency for indirect experiments by adaptively designing a data collection policy over instrumental variables. Our main contribution is a practical computational procedure that utilizes influence functions to search for an optimal data collection policy, minimizing the mean-squared error of the desired (non-linear) estimator. Through experiments conducted in various domains inspired by real-world applications, we showcase how our method can significantly improve the sample efficiency of indirect experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.02438v1-abstract-full').style.display = 'none'; document.getElementById('2312.02438v1-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> 4 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.14641">arXiv:2311.14641</a> <span> [<a href="https://arxiv.org/pdf/2311.14641">pdf</a>, <a href="https://arxiv.org/format/2311.14641">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1038/s41467-024-52259-9">10.1038/s41467-024-52259-9 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pedersen%2C+J+E">Jens E. Pedersen</a>, <a href="/search/cs?searchtype=author&query=Abreu%2C+S">Steven Abreu</a>, <a href="/search/cs?searchtype=author&query=Jobst%2C+M">Matthias Jobst</a>, <a href="/search/cs?searchtype=author&query=Lenz%2C+G">Gregor Lenz</a>, <a href="/search/cs?searchtype=author&query=Fra%2C+V">Vittorio Fra</a>, <a href="/search/cs?searchtype=author&query=Bauer%2C+F+C">Felix C. Bauer</a>, <a href="/search/cs?searchtype=author&query=Muir%2C+D+R">Dylan R. Muir</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+P">Peng Zhou</a>, <a href="/search/cs?searchtype=author&query=Vogginger%2C+B">Bernhard Vogginger</a>, <a href="/search/cs?searchtype=author&query=Heckel%2C+K">Kade Heckel</a>, <a href="/search/cs?searchtype=author&query=Urgese%2C+G">Gianvito Urgese</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sadasivan Shankar</a>, <a href="/search/cs?searchtype=author&query=Stewart%2C+T+C">Terrence C. Stewart</a>, <a href="/search/cs?searchtype=author&query=Sheik%2C+S">Sadique Sheik</a>, <a href="/search/cs?searchtype=author&query=Eshraghian%2C+J+K">Jason K. Eshraghian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.14641v2-abstract-short" style="display: inline;"> Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for neural dynamics, there exists numerous software and hardware solutions and stacks whose variability makes it difficult to reproduce findings. Here, we est… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.14641v2-abstract-full').style.display = 'inline'; document.getElementById('2311.14641v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.14641v2-abstract-full" style="display: none;"> Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for neural dynamics, there exists numerous software and hardware solutions and stacks whose variability makes it difficult to reproduce findings. Here, we establish a common reference frame for computations in digital neuromorphic systems, titled Neuromorphic Intermediate Representation (NIR). NIR defines a set of computational and composable model primitives as hybrid systems combining continuous-time dynamics and discrete events. By abstracting away assumptions around discretization and hardware constraints, NIR faithfully captures the computational model, while bridging differences between the evaluated implementation and the underlying mathematical formalism. NIR supports an unprecedented number of neuromorphic systems, which we demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms. NIR decouples the development of neuromorphic hardware and software, enabling interoperability between platforms and improving accessibility to multiple neuromorphic technologies. We believe that NIR is a key next step in brain-inspired hardware-software co-evolution, enabling research towards the implementation of energy efficient computational principles of nervous systems. NIR is available at neuroir.org <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.14641v2-abstract-full').style.display = 'none'; document.getElementById('2311.14641v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NIR is available at https://neuroir.org</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Nat Commun 15, 8122 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.07516">arXiv:2310.07516</a> <span> [<a href="https://arxiv.org/pdf/2310.07516">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Energy Estimates Across Layers of Computing: From Devices to Large-Scale Applications in Machine Learning for Natural Language Processing, Scientific Computing, and Cryptocurrency Mining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sadasivan Shankar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.07516v1-abstract-short" style="display: inline;"> Estimates of energy usage in layers of computing from devices to algorithms have been determined and analyzed. Building on the previous analysis [3], energy needed from single devices and systems including three large-scale computing applications such as Artificial Intelligence (AI)/Machine Learning for Natural Language Processing, Scientific Simulations, and Cryptocurrency Mining have been estima… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.07516v1-abstract-full').style.display = 'inline'; document.getElementById('2310.07516v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.07516v1-abstract-full" style="display: none;"> Estimates of energy usage in layers of computing from devices to algorithms have been determined and analyzed. Building on the previous analysis [3], energy needed from single devices and systems including three large-scale computing applications such as Artificial Intelligence (AI)/Machine Learning for Natural Language Processing, Scientific Simulations, and Cryptocurrency Mining have been estimated. In contrast to the bit-level switching, in which transistors achieved energy efficiency due to geometrical scaling, higher energy is expended both at the at the instructions and simulations levels of an application. Additionally, the analysis based on AI/ML Accelerators indicate that changes in architectures using an older semiconductor technology node have comparable energy efficiency with a different architecture using a newer technology. Further comparisons of the energy in computing systems with the thermodynamic and biological limits, indicate that there is a 27-36 orders of magnitude higher energy requirements for total simulation of an application. These energy estimates underscore the need for serious considerations of energy efficiency in computing by including energy as a design parameter, enabling growing needs of compute-intensive applications in a digital world. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.07516v1-abstract-full').style.display = 'none'; document.getElementById('2310.07516v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 5 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> C.3; C.4; I.2; J.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.07000">arXiv:2310.07000</a> <span> [<a href="https://arxiv.org/pdf/2310.07000">pdf</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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> CarDS-Plus ECG Platform: Development and Feasibility Evaluation of a Multiplatform Artificial Intelligence Toolkit for Portable and Wearable Device Electrocardiograms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S+V">Sumukh Vasisht Shankar</a>, <a href="/search/cs?searchtype=author&query=Oikonomou%2C+E+K">Evangelos K Oikonomou</a>, <a href="/search/cs?searchtype=author&query=Khera%2C+R">Rohan Khera</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.07000v1-abstract-short" style="display: inline;"> In the rapidly evolving landscape of modern healthcare, the integration of wearable & portable technology provides a unique opportunity for personalized health monitoring in the community. Devices like the Apple Watch, FitBit, and AliveCor KardiaMobile have revolutionized the acquisition and processing of intricate health data streams. Amidst the variety of data collected by these gadgets, single-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.07000v1-abstract-full').style.display = 'inline'; document.getElementById('2310.07000v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.07000v1-abstract-full" style="display: none;"> In the rapidly evolving landscape of modern healthcare, the integration of wearable & portable technology provides a unique opportunity for personalized health monitoring in the community. Devices like the Apple Watch, FitBit, and AliveCor KardiaMobile have revolutionized the acquisition and processing of intricate health data streams. Amidst the variety of data collected by these gadgets, single-lead electrocardiogram (ECG) recordings have emerged as a crucial source of information for monitoring cardiovascular health. There has been significant advances in artificial intelligence capable of interpreting these 1-lead ECGs, facilitating clinical diagnosis as well as the detection of rare cardiac disorders. This design study describes the development of an innovative multiplatform system aimed at the rapid deployment of AI-based ECG solutions for clinical investigation & care delivery. The study examines design considerations, aligning them with specific applications, develops data flows to maximize efficiency for research & clinical use. This process encompasses the reception of single-lead ECGs from diverse wearable devices, channeling this data into a centralized data lake & facilitating real-time inference through AI models for ECG interpretation. An evaluation of the platform demonstrates a mean duration from acquisition to reporting of results of 33.0 to 35.7 seconds, after a standard 30 second acquisition. There were no substantial differences in acquisition to reporting across two commercially available devices (Apple Watch and KardiaMobile). These results demonstrate the succcessful translation of design principles into a fully integrated & efficient strategy for leveraging 1-lead ECGs across platforms & interpretation by AI-ECG algorithms. Such a platform is critical to translating AI discoveries for wearable and portable ECG devices to clinical impact through rapid deployment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.07000v1-abstract-full').style.display = 'none'; document.getElementById('2310.07000v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.03854">arXiv:2308.03854</a> <span> [<a href="https://arxiv.org/pdf/2308.03854">pdf</a>, <a href="https://arxiv.org/ps/2308.03854">ps</a>, <a href="https://arxiv.org/format/2308.03854">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</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="Human-Computer Interaction">cs.HC</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"> Revisiting Prompt Engineering via Declarative Crowdsourcing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Asawa%2C+P">Parth Asawa</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+N">Naman Jain</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yujie Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.03854v1-abstract-short" style="display: inline;"> Large language models (LLMs) are incredibly powerful at comprehending and generating data in the form of text, but are brittle and error-prone. There has been an advent of toolkits and recipes centered around so-called prompt engineering-the process of asking an LLM to do something via a series of prompts. However, for LLM-powered data processing workflows, in particular, optimizing for quality, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03854v1-abstract-full').style.display = 'inline'; document.getElementById('2308.03854v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.03854v1-abstract-full" style="display: none;"> Large language models (LLMs) are incredibly powerful at comprehending and generating data in the form of text, but are brittle and error-prone. There has been an advent of toolkits and recipes centered around so-called prompt engineering-the process of asking an LLM to do something via a series of prompts. However, for LLM-powered data processing workflows, in particular, optimizing for quality, while keeping cost bounded, is a tedious, manual process. We put forth a vision for declarative prompt engineering. We view LLMs like crowd workers and leverage ideas from the declarative crowdsourcing literature-including leveraging multiple prompting strategies, ensuring internal consistency, and exploring hybrid-LLM-non-LLM approaches-to make prompt engineering a more principled process. Preliminary case studies on sorting, entity resolution, and imputation demonstrate the promise of our approach <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03854v1-abstract-full').style.display = 'none'; document.getElementById('2308.03854v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.06094">arXiv:2303.06094</a> <span> [<a href="https://arxiv.org/pdf/2303.06094">pdf</a>, <a href="https://arxiv.org/format/2303.06094">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Moving Fast With Broken Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Fawaz%2C+L">Labib Fawaz</a>, <a href="/search/cs?searchtype=author&query=Gyllstrom%2C+K">Karl Gyllstrom</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.06094v1-abstract-short" style="display: inline;"> Machine learning (ML) models in production pipelines are frequently retrained on the latest partitions of large, continually-growing datasets. Due to engineering bugs, partitions in such datasets almost always have some corrupted features; thus, it's critical to detect data issues and block retraining before downstream ML model accuracy decreases. However, it's difficult to identify when a partiti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06094v1-abstract-full').style.display = 'inline'; document.getElementById('2303.06094v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.06094v1-abstract-full" style="display: none;"> Machine learning (ML) models in production pipelines are frequently retrained on the latest partitions of large, continually-growing datasets. Due to engineering bugs, partitions in such datasets almost always have some corrupted features; thus, it's critical to detect data issues and block retraining before downstream ML model accuracy decreases. However, it's difficult to identify when a partition is corrupted enough to block retraining. Blocking too often yields stale model snapshots in production; blocking too little yields broken model snapshots in production. In this paper, we present an automatic data validation system for ML pipelines implemented at Meta. We employ what we call a Partition Summarization (PS) approach to data validation: each timestamp-based partition of data is summarized with data quality metrics, and summaries are compared to detect corrupted partitions. We describe how we can adapt PS for several data validation methods and compare their pros and cons. Since none of the methods by themselves met our requirements for high precision and recall in detecting corruptions, we devised GATE, our high-precision and recall data validation method. GATE gave a 2.1x average improvement in precision over the baseline on a case study with Instagram's data. Finally, we discuss lessons learned from implementing data validation for Meta's production ML pipelines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06094v1-abstract-full').style.display = 'none'; document.getElementById('2303.06094v1-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">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 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/2303.02374">arXiv:2303.02374</a> <span> [<a href="https://arxiv.org/pdf/2303.02374">pdf</a>, <a href="https://arxiv.org/format/2303.02374">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Social Media COVID-19 Contact Tracing Using Mobile Social Payments and Facebook Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shrivu Shankar</a>, <a href="/search/cs?searchtype=author&query=Murthy%2C+D">Dhiraj Murthy</a>, <a href="/search/cs?searchtype=author&query=Dashtian%2C+H">Hassan Dashtian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.02374v1-abstract-short" style="display: inline;"> Many in the US were reluctant to report their COVID-19 cases at the height of the pandemic (e.g., for fear of missing work or other obligations due to quarantine mandates). Other methods such as using public social media data can therefore help augment current approaches to surveilling pandemics. This study evaluated the effectiveness of using social media data as a data source for tracking public… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.02374v1-abstract-full').style.display = 'inline'; document.getElementById('2303.02374v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.02374v1-abstract-full" style="display: none;"> Many in the US were reluctant to report their COVID-19 cases at the height of the pandemic (e.g., for fear of missing work or other obligations due to quarantine mandates). Other methods such as using public social media data can therefore help augment current approaches to surveilling pandemics. This study evaluated the effectiveness of using social media data as a data source for tracking public health pandemics. There have been several attempts at using social media data from platforms like Twitter for analyzing the COVID-19 pandemic. While these provide a multitude of useful insights, new platforms like Venmo, a popular U.S. mobile social payment app often used during in-person activities, remain understudied. We developed unique computational methods (combining Venmo- and Facebook- derived data) to classify post content, including the location where the content was likely posted. This approach enabled geotemporal COVID-19-related infoveillance. By examining 135M publicly available Venmo transactions from 22.1M unique users, we found significant spikes in the use of COVID-19 related keywords in March 2020. Using Facebook-based geotags for 9K users along with transaction geo-parsing (i.e., parsing text to detect place names), we identified 38K location-based clusters. Within these groups, we found a strong correlation (0.81) between the use of COVID-19 keywords in a region and the number of reported COVID-19 cases as well as an aggregate decrease in transactions during lockdowns and an increase when lockdowns are lifted. Surprisingly, we saw a weak negative correlation between the number of transactions and reported cases over time (-0.49). Our results indicate that using non-Twitter social media trace data can aid pandemic- and other health-related infoveillance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.02374v1-abstract-full').style.display = 'none'; document.getElementById('2303.02374v1-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> 4 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.03161">arXiv:2302.03161</a> <span> [<a href="https://arxiv.org/pdf/2302.03161">pdf</a>, <a href="https://arxiv.org/format/2302.03161">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"> Optimization using Parallel Gradient Evaluations on Multiple Parameters </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chandak%2C+Y">Yash Chandak</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Gandikota%2C+V">Venkata Gandikota</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+P+S">Philip S. Thomas</a>, <a href="/search/cs?searchtype=author&query=Mazumdar%2C+A">Arya Mazumdar</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="2302.03161v1-abstract-short" style="display: inline;"> We propose a first-order method for convex optimization, where instead of being restricted to the gradient from a single parameter, gradients from multiple parameters can be used during each step of gradient descent. This setup is particularly useful when a few processors are available that can be used in parallel for optimization. Our method uses gradients from multiple parameters in synergy to u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03161v1-abstract-full').style.display = 'inline'; document.getElementById('2302.03161v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.03161v1-abstract-full" style="display: none;"> We propose a first-order method for convex optimization, where instead of being restricted to the gradient from a single parameter, gradients from multiple parameters can be used during each step of gradient descent. This setup is particularly useful when a few processors are available that can be used in parallel for optimization. Our method uses gradients from multiple parameters in synergy to update these parameters together towards the optima. While doing so, it is ensured that the computational and memory complexity is of the same order as that of gradient descent. Empirical results demonstrate that even using gradients from as low as \textit{two} parameters, our method can often obtain significant acceleration and provide robustness to hyper-parameter settings. We remark that the primary goal of this work is less theoretical, and is instead aimed at exploring the understudied case of using multiple gradients during each step of optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03161v1-abstract-full').style.display = 'none'; document.getElementById('2302.03161v1-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at OPT workshop @ Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.10330">arXiv:2301.10330</a> <span> [<a href="https://arxiv.org/pdf/2301.10330">pdf</a>, <a href="https://arxiv.org/format/2301.10330">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> </div> </div> <p class="title is-5 mathjax"> Off-Policy Evaluation for Action-Dependent Non-Stationary Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chandak%2C+Y">Yash Chandak</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Bastian%2C+N+D">Nathaniel D. Bastian</a>, <a href="/search/cs?searchtype=author&query=da+Silva%2C+B+C">Bruno Castro da Silva</a>, <a href="/search/cs?searchtype=author&query=Brunskil%2C+E">Emma Brunskil</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+P+S">Philip S. Thomas</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="2301.10330v1-abstract-short" style="display: inline;"> Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes due to external factors (passive non-stationarity), changes induced by interactions with the system itself (active non-stationarity), or both (hybrid non-station… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.10330v1-abstract-full').style.display = 'inline'; document.getElementById('2301.10330v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.10330v1-abstract-full" style="display: none;"> Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes due to external factors (passive non-stationarity), changes induced by interactions with the system itself (active non-stationarity), or both (hybrid non-stationarity). In this work, we take the first steps towards the fundamental challenge of on-policy and off-policy evaluation amidst structured changes due to active, passive, or hybrid non-stationarity. Towards this goal, we make a higher-order stationarity assumption such that non-stationarity results in changes over time, but the way changes happen is fixed. We propose, OPEN, an algorithm that uses a double application of counterfactual reasoning and a novel importance-weighted instrument-variable regression to obtain both a lower bias and a lower variance estimate of the structure in the changes of a policy's past performances. Finally, we show promising results on how OPEN can be used to predict future performances for several domains inspired by real-world applications that exhibit non-stationarity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.10330v1-abstract-full').style.display = 'none'; document.getElementById('2301.10330v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.11649">arXiv:2211.11649</a> <span> [<a href="https://arxiv.org/pdf/2211.11649">pdf</a>, <a href="https://arxiv.org/format/2211.11649">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> </div> </div> <p class="title is-5 mathjax"> Implicit Training of Energy Model for Structure Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Piratla%2C+V">Vihari Piratla</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="2211.11649v1-abstract-short" style="display: inline;"> Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of standard losses. When the objective aligns well with the evaluation metric, this is not a major issue. However when dealing with complex structured outputs, the ideal objective can be hard to optimize and the efficacy of us… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.11649v1-abstract-full').style.display = 'inline'; document.getElementById('2211.11649v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.11649v1-abstract-full" style="display: none;"> Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of standard losses. When the objective aligns well with the evaluation metric, this is not a major issue. However when dealing with complex structured outputs, the ideal objective can be hard to optimize and the efficacy of usual objectives as a proxy for the true objective can be questionable. In this work, we argue that the existing inference network based structure prediction methods ( Tu and Gimpel 2018; Tu, Pang, and Gimpel 2020) are indirectly learning to optimize a dynamic loss objective parameterized by the energy model. We then explore using implicit-gradient based technique to learn the corresponding dynamic objectives. Our experiments show that implicitly learning a dynamic loss landscape is an effective method for improving model performance in structure prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.11649v1-abstract-full').style.display = 'none'; document.getElementById('2211.11649v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">AAAI</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.03758">arXiv:2211.03758</a> <span> [<a href="https://arxiv.org/pdf/2211.03758">pdf</a>, <a href="https://arxiv.org/format/2211.03758">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Privacy Aware Experiments without Cookies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+R">Ritwik Sinha</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Saayan Mitra</a>, <a href="/search/cs?searchtype=author&query=Swaminathan%2C+V">Viswanathan Swaminathan</a>, <a href="/search/cs?searchtype=author&query=Mahadevan%2C+S">Sridhar Mahadevan</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+M">Moumita Sinha</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="2211.03758v2-abstract-short" style="display: inline;"> Consider two brands that want to jointly test alternate web experiences for their customers with an A/B test. Such collaborative tests are today enabled using \textit{third-party cookies}, where each brand has information on the identity of visitors to another website. With the imminent elimination of third-party cookies, such A/B tests will become untenable. We propose a two-stage experimental de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.03758v2-abstract-full').style.display = 'inline'; document.getElementById('2211.03758v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.03758v2-abstract-full" style="display: none;"> Consider two brands that want to jointly test alternate web experiences for their customers with an A/B test. Such collaborative tests are today enabled using \textit{third-party cookies}, where each brand has information on the identity of visitors to another website. With the imminent elimination of third-party cookies, such A/B tests will become untenable. We propose a two-stage experimental design, where the two brands only need to agree on high-level aggregate parameters of the experiment to test the alternate experiences. Our design respects the privacy of customers. We propose an estimater of the Average Treatment Effect (ATE), show that it is unbiased and theoretically compute its variance. Our demonstration describes how a marketer for a brand can design such an experiment and analyze the results. On real and simulated data, we show that the approach provides valid estimate of the ATE with low variance and is robust to the proportion of visitors overlapping across the brands. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.03758v2-abstract-full').style.display = 'none'; document.getElementById('2211.03758v2-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Technical report supplementing paper accepted to WSDM 23</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.17331">arXiv:2210.17331</a> <span> [<a href="https://arxiv.org/pdf/2210.17331">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/HPEC55821.2022.9926296">10.1109/HPEC55821.2022.9926296 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Trends in Energy Estimates for Computing in AI/Machine Learning Accelerators, Supercomputers, and Compute-Intensive Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sadasivan Shankar</a>, <a href="/search/cs?searchtype=author&query=Reuther%2C+A">Albert Reuther</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="2210.17331v1-abstract-short" style="display: inline;"> We examine the computational energy requirements of different systems driven by the geometrical scaling law, and increasing use of Artificial Intelligence or Machine Learning (AI-ML) over the last decade. With more scientific and technology applications based on data-driven discovery, machine learning methods, especially deep neural networks, have become widely used. In order to enable such applic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.17331v1-abstract-full').style.display = 'inline'; document.getElementById('2210.17331v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.17331v1-abstract-full" style="display: none;"> We examine the computational energy requirements of different systems driven by the geometrical scaling law, and increasing use of Artificial Intelligence or Machine Learning (AI-ML) over the last decade. With more scientific and technology applications based on data-driven discovery, machine learning methods, especially deep neural networks, have become widely used. In order to enable such applications, both hardware accelerators and advanced AI-ML methods have led to the introduction of new architectures, system designs, algorithms, and software. Our analysis of energy trends indicates three important observations: 1) Energy efficiency due to geometrical scaling is slowing down; 2) The energy efficiency at the bit-level does not translate into efficiency at the instruction-level, or at the system-level for a variety of systems, especially for large-scale AI-ML accelerators or supercomputers; 3) At the application level, general-purpose AI-ML methods can be computationally energy intensive, off-setting the gains in energy from geometrical scaling and special purpose accelerators. Further, our analysis provides specific pointers for integrating energy efficiency with performance analysis for enabling high-performance and sustainable computing in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.17331v1-abstract-full').style.display = 'none'; document.getElementById('2210.17331v1-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 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 pages, 9 figures, Submitted to Proceedings of IEEE Conference on High Performance Extreme Computing (HPEC) 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68U01 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> C.4; I.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.09125">arXiv:2209.09125</a> <span> [<a href="https://arxiv.org/pdf/2209.09125">pdf</a>, <a href="https://arxiv.org/format/2209.09125">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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"> Operationalizing Machine Learning: An Interview Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Garcia%2C+R">Rolando Garcia</a>, <a href="/search/cs?searchtype=author&query=Hellerstein%2C+J+M">Joseph M. Hellerstein</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</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="2209.09125v1-abstract-short" style="display: inline;"> Organizations rely on machine learning engineers (MLEs) to operationalize ML, i.e., deploy and maintain ML pipelines in production. The process of operationalizing ML, or MLOps, consists of a continual loop of (i) data collection and labeling, (ii) experimentation to improve ML performance, (iii) evaluation throughout a multi-staged deployment process, and (iv) monitoring of performance drops in p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.09125v1-abstract-full').style.display = 'inline'; document.getElementById('2209.09125v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.09125v1-abstract-full" style="display: none;"> Organizations rely on machine learning engineers (MLEs) to operationalize ML, i.e., deploy and maintain ML pipelines in production. The process of operationalizing ML, or MLOps, consists of a continual loop of (i) data collection and labeling, (ii) experimentation to improve ML performance, (iii) evaluation throughout a multi-staged deployment process, and (iv) monitoring of performance drops in production. When considered together, these responsibilities seem staggering -- how does anyone do MLOps, what are the unaddressed challenges, and what are the implications for tool builders? We conducted semi-structured ethnographic interviews with 18 MLEs working across many applications, including chatbots, autonomous vehicles, and finance. Our interviews expose three variables that govern success for a production ML deployment: Velocity, Validation, and Versioning. We summarize common practices for successful ML experimentation, deployment, and sustaining production performance. Finally, we discuss interviewees' pain points and anti-patterns, with implications for tool design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.09125v1-abstract-full').style.display = 'none'; document.getElementById('2209.09125v1-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">20 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/2209.03056">arXiv:2209.03056</a> <span> [<a href="https://arxiv.org/pdf/2209.03056">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Parallel and Streaming Wavelet Neural Networks for Classification and Regression under Apache Spark </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Venkatesh%2C+E+H">Eduru Harindra Venkatesh</a>, <a href="/search/cs?searchtype=author&query=Vivek%2C+Y">Yelleti Vivek</a>, <a href="/search/cs?searchtype=author&query=Ravi%2C+V">Vadlamani Ravi</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+O+S">Orsu Shiva Shankar</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="2209.03056v1-abstract-short" style="display: inline;"> Wavelet neural networks (WNN) have been applied in many fields to solve regression as well as classification problems. After the advent of big data, as data gets generated at a brisk pace, it is imperative to analyze it as soon as it is generated owing to the fact that the nature of the data may change dramatically in short time intervals. This is necessitated by the fact that big data is all perv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.03056v1-abstract-full').style.display = 'inline'; document.getElementById('2209.03056v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.03056v1-abstract-full" style="display: none;"> Wavelet neural networks (WNN) have been applied in many fields to solve regression as well as classification problems. After the advent of big data, as data gets generated at a brisk pace, it is imperative to analyze it as soon as it is generated owing to the fact that the nature of the data may change dramatically in short time intervals. This is necessitated by the fact that big data is all pervasive and throws computational challenges for data scientists. Therefore, in this paper, we built an efficient Scalable, Parallelized Wavelet Neural Network (SPWNN) which employs the parallel stochastic gradient algorithm (SGD) algorithm. SPWNN is designed and developed under both static and streaming environments in the horizontal parallelization framework. SPWNN is implemented by using Morlet and Gaussian functions as activation functions. This study is conducted on big datasets like gas sensor data which has more than 4 million samples and medical research data which has more than 10,000 features, which are high dimensional in nature. The experimental analysis indicates that in the static environment, SPWNN with Morlet activation function outperformed SPWNN with Gaussian on the classification datasets. However, in the case of regression, the opposite was observed. In contrast, in the streaming environment i.e., Gaussian outperformed Morlet on the classification and Morlet outperformed Gaussian on the regression datasets. Overall, the proposed SPWNN architecture achieved a speedup of 1.32-1.40. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.03056v1-abstract-full').style.display = 'none'; document.getElementById('2209.03056v1-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">25 pages; 2 Tables; 7 Figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T09; 68Txx <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.00302">arXiv:2209.00302</a> <span> [<a href="https://arxiv.org/pdf/2209.00302">pdf</a>, <a href="https://arxiv.org/format/2209.00302">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="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> Progressive Fusion for Multimodal Integration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+L">Laure Thompson</a>, <a href="/search/cs?searchtype=author&query=Fiterau%2C+M">Madalina Fiterau</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="2209.00302v2-abstract-short" style="display: inline;"> Integration of multimodal information from various sources has been shown to boost the performance of machine learning models and thus has received increased attention in recent years. Often such models use deep modality-specific networks to obtain unimodal features which are combined to obtain "late-fusion" representations. However, these designs run the risk of information loss in the respective… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.00302v2-abstract-full').style.display = 'inline'; document.getElementById('2209.00302v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.00302v2-abstract-full" style="display: none;"> Integration of multimodal information from various sources has been shown to boost the performance of machine learning models and thus has received increased attention in recent years. Often such models use deep modality-specific networks to obtain unimodal features which are combined to obtain "late-fusion" representations. However, these designs run the risk of information loss in the respective unimodal pipelines. On the other hand, "early-fusion" methodologies, which combine features early, suffer from the problems associated with feature heterogeneity and high sample complexity. In this work, we present an iterative representation refinement approach, called Progressive Fusion, which mitigates the issues with late fusion representations. Our model-agnostic technique introduces backward connections that make late stage fused representations available to early layers, improving the expressiveness of the representations at those stages, while retaining the advantages of late fusion designs. We test Progressive Fusion on tasks including affective sentiment detection, multimedia analysis, and time series fusion with different models, demonstrating its versatility. We show that our approach consistently improves performance, for instance attaining a 5% reduction in MSE and 40% improvement in robustness on multimodal time series prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.00302v2-abstract-full').style.display = 'none'; document.getElementById('2209.00302v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 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/2205.11473">arXiv:2205.11473</a> <span> [<a href="https://arxiv.org/pdf/2205.11473">pdf</a>, <a href="https://arxiv.org/format/2205.11473">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"> Rethinking Streaming Machine Learning Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Herman%2C+B">Bernease Herman</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.11473v1-abstract-short" style="display: inline;"> While most work on evaluating machine learning (ML) models focuses on computing accuracy on batches of data, tracking accuracy alone in a streaming setting (i.e., unbounded, timestamp-ordered datasets) fails to appropriately identify when models are performing unexpectedly. In this position paper, we discuss how the nature of streaming ML problems introduces new real-world challenges (e.g., delaye… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.11473v1-abstract-full').style.display = 'inline'; document.getElementById('2205.11473v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.11473v1-abstract-full" style="display: none;"> While most work on evaluating machine learning (ML) models focuses on computing accuracy on batches of data, tracking accuracy alone in a streaming setting (i.e., unbounded, timestamp-ordered datasets) fails to appropriately identify when models are performing unexpectedly. In this position paper, we discuss how the nature of streaming ML problems introduces new real-world challenges (e.g., delayed arrival of labels) and recommend additional metrics to assess streaming ML performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.11473v1-abstract-full').style.display = 'none'; document.getElementById('2205.11473v1-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ML Evaluation Standards Workshop (ICLR 2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.00385">arXiv:2110.00385</a> <span> [<a href="https://arxiv.org/pdf/2110.00385">pdf</a>, <a href="https://arxiv.org/ps/2110.00385">ps</a>, <a href="https://arxiv.org/format/2110.00385">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Neural Dependency Coding inspired Multimodal Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</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="2110.00385v2-abstract-short" style="display: inline;"> Information integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different sensory perceptive fields to interact with the environment and each other. Recent work in deep fusion models via neural networks has led to substantial improvements over unimodal approaches in areas l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.00385v2-abstract-full').style.display = 'inline'; document.getElementById('2110.00385v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.00385v2-abstract-full" style="display: none;"> Information integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different sensory perceptive fields to interact with the environment and each other. Recent work in deep fusion models via neural networks has led to substantial improvements over unimodal approaches in areas like speech recognition, emotion recognition and analysis, captioning and image description. However, such research has mostly focused on architectural changes allowing for fusion of different modalities while keeping the model complexity manageable. Inspired by recent neuroscience ideas about multisensory integration and processing, we investigate the effect of synergy maximizing loss functions. Experiments on multimodal sentiment analysis tasks: CMU-MOSI and CMU-MOSEI with different models show that our approach provides a consistent performance boost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.00385v2-abstract-full').style.display = 'none'; document.getElementById('2110.00385v2-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> 4 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 September, 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/2108.13557">arXiv:2108.13557</a> <span> [<a href="https://arxiv.org/pdf/2108.13557">pdf</a>, <a href="https://arxiv.org/format/2108.13557">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Towards Observability for Production Machine Learning Pipelines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A">Aditya Parameswaran</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="2108.13557v3-abstract-short" style="display: inline;"> Software organizations are increasingly incorporating machine learning (ML) into their product offerings, driving a need for new data management tools. Many of these tools facilitate the initial development of ML applications, but sustaining these applications post-deployment is difficult due to lack of real-time feedback (i.e., labels) for predictions and silent failures that could occur at any c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.13557v3-abstract-full').style.display = 'inline'; document.getElementById('2108.13557v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.13557v3-abstract-full" style="display: none;"> Software organizations are increasingly incorporating machine learning (ML) into their product offerings, driving a need for new data management tools. Many of these tools facilitate the initial development of ML applications, but sustaining these applications post-deployment is difficult due to lack of real-time feedback (i.e., labels) for predictions and silent failures that could occur at any component of the ML pipeline (e.g., data distribution shift or anomalous features). We propose a new type of data management system that offers end-to-end observability, or visibility into complex system behavior, for deployed ML pipelines through assisted (1) detection, (2) diagnosis, and (3) reaction to ML-related bugs. We describe new research challenges and suggest preliminary solution ideas in all three aspects. Finally, we introduce an example architecture for a "bolt-on" ML observability system, or one that wraps around existing tools in the stack. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.13557v3-abstract-full').style.display = 'none'; document.getElementById('2108.13557v3-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">11 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.12982">arXiv:2108.12982</a> <span> [<a href="https://arxiv.org/pdf/2108.12982">pdf</a>, <a href="https://arxiv.org/format/2108.12982">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"> Adversarial Stein Training for Graph Energy Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</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="2108.12982v1-abstract-short" style="display: inline;"> Learning distributions over graph-structured data is a challenging task with many applications in biology and chemistry. In this work we use an energy-based model (EBM) based on multi-channel graph neural networks (GNN) to learn permutation invariant unnormalized density functions on graphs. Unlike standard EBM training methods our approach is to learn the model via minimizing adversarial stein di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12982v1-abstract-full').style.display = 'inline'; document.getElementById('2108.12982v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.12982v1-abstract-full" style="display: none;"> Learning distributions over graph-structured data is a challenging task with many applications in biology and chemistry. In this work we use an energy-based model (EBM) based on multi-channel graph neural networks (GNN) to learn permutation invariant unnormalized density functions on graphs. Unlike standard EBM training methods our approach is to learn the model via minimizing adversarial stein discrepancy. Samples from the model can be obtained via Langevin dynamics based MCMC. We find that this approach achieves competitive results on graph generation compared to benchmark models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12982v1-abstract-full').style.display = 'none'; document.getElementById('2108.12982v1-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 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">Appeared at Machine Learning for Molecules Workshop at NeurIPS 2020.https://ml4molecules.github.io</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.09569">arXiv:2108.09569</a> <span> [<a href="https://arxiv.org/pdf/2108.09569">pdf</a>, <a href="https://arxiv.org/format/2108.09569">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/CONECCT52877.2021.9622534">10.1109/CONECCT52877.2021.9622534 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Wireless Sensor Networks for Optimisation of Search and Rescue Management in Floods </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bhatt%2C+H">Harshil Bhatt</a>, <a href="/search/cs?searchtype=author&query=G%2C+P">Pranesh G</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Samarth Shankar</a>, <a href="/search/cs?searchtype=author&query=Haralikar%2C+S">Shriyash Haralikar</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="2108.09569v1-abstract-short" style="display: inline;"> We propose a novel search-and-rescue management method that relies on the aerial deployment of Wireless Sensor Network (WSN) for locating victims after floods. The sensor nodes will collect vital information such as heat signatures for detecting human presence and location, the flow of flood. The sensor modules are packed in a portable floating buoy with a user interface to convey emergency messag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.09569v1-abstract-full').style.display = 'inline'; document.getElementById('2108.09569v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.09569v1-abstract-full" style="display: none;"> We propose a novel search-and-rescue management method that relies on the aerial deployment of Wireless Sensor Network (WSN) for locating victims after floods. The sensor nodes will collect vital information such as heat signatures for detecting human presence and location, the flow of flood. The sensor modules are packed in a portable floating buoy with a user interface to convey emergency messages to the base station. Sensor nodes are designed based on disaster conditions, cost-effectiveness and deployed in the affected region by a centrifugal dispersion system from a helicopter. A mobile ad-hoc network is set up by modifying the Low Energy Adaptive Cluster Hierarchy (LEACH) protocol for greater efficiency and adoption of multi-hop of Cluster Heads for long-distance communication to Base Station. The model metrics have been defined considering previous rural floods in India. The efficiency and power characteristics of the network are compared to other protocols via simulations. The sensor data from the network makes resource management, rescue planning and emergency priority more efficient, thus saving more lives from floods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.09569v1-abstract-full').style.display = 'none'; document.getElementById('2108.09569v1-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 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.09047">arXiv:2108.09047</a> <span> [<a href="https://arxiv.org/pdf/2108.09047">pdf</a>, <a href="https://arxiv.org/format/2108.09047">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/IROS45743.2020.9341724">10.1109/IROS45743.2020.9341724 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AutoLay: Benchmarking amodal layout estimation for autonomous driving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mani%2C+K">Kaustubh Mani</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+N+S">N. Sai Shankar</a>, <a href="/search/cs?searchtype=author&query=Jatavallabhula%2C+K+M">Krishna Murthy Jatavallabhula</a>, <a href="/search/cs?searchtype=author&query=Krishna%2C+K+M">K. Madhava Krishna</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="2108.09047v1-abstract-short" style="display: inline;"> Given an image or a video captured from a monocular camera, amodal layout estimation is the task of predicting semantics and occupancy in bird's eye view. The term amodal implies we also reason about entities in the scene that are occluded or truncated in image space. While several recent efforts have tackled this problem, there is a lack of standardization in task specification, datasets, and eva… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.09047v1-abstract-full').style.display = 'inline'; document.getElementById('2108.09047v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.09047v1-abstract-full" style="display: none;"> Given an image or a video captured from a monocular camera, amodal layout estimation is the task of predicting semantics and occupancy in bird's eye view. The term amodal implies we also reason about entities in the scene that are occluded or truncated in image space. While several recent efforts have tackled this problem, there is a lack of standardization in task specification, datasets, and evaluation protocols. We address these gaps with AutoLay, a dataset and benchmark for amodal layout estimation from monocular images. AutoLay encompasses driving imagery from two popular datasets: KITTI and Argoverse. In addition to fine-grained attributes such as lanes, sidewalks, and vehicles, we also provide semantically annotated 3D point clouds. We implement several baselines and bleeding edge approaches, and release our data and code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.09047v1-abstract-full').style.display = 'none'; document.getElementById('2108.09047v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">published in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.01338">arXiv:2107.01338</a> <span> [<a href="https://arxiv.org/pdf/2107.01338">pdf</a>, <a href="https://arxiv.org/format/2107.01338">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> </div> </div> <p class="title is-5 mathjax"> Sibling Regression for Generalized Linear Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Sheldon%2C+D">Daniel Sheldon</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="2107.01338v2-abstract-short" style="display: inline;"> Field observations form the basis of many scientific studies, especially in ecological and social sciences. Despite efforts to conduct such surveys in a standardized way, observations can be prone to systematic measurement errors. The removal of systematic variability introduced by the observation process, if possible, can greatly increase the value of this data. Existing non-parametric techniques… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.01338v2-abstract-full').style.display = 'inline'; document.getElementById('2107.01338v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.01338v2-abstract-full" style="display: none;"> Field observations form the basis of many scientific studies, especially in ecological and social sciences. Despite efforts to conduct such surveys in a standardized way, observations can be prone to systematic measurement errors. The removal of systematic variability introduced by the observation process, if possible, can greatly increase the value of this data. Existing non-parametric techniques for correcting such errors assume linear additive noise models. This leads to biased estimates when applied to generalized linear models (GLM). We present an approach based on residual functions to address this limitation. We then demonstrate its effectiveness on synthetic data and show it reduces systematic detection variability in moth surveys. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.01338v2-abstract-full').style.display = 'none'; document.getElementById('2107.01338v2-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 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ECMLPKDD-2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.08321">arXiv:2105.08321</a> <span> [<a href="https://arxiv.org/pdf/2105.08321">pdf</a>, <a href="https://arxiv.org/format/2105.08321">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Can Self Reported Symptoms Predict Daily COVID-19 Cases? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=Reddy%2C+V">Viswanatha Reddy</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=TV%2C+S">Sethuraman TV</a>, <a href="/search/cs?searchtype=author&query=Nashnoush%2C+E">Eptehal Nashnoush</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Kaur%2C+R">Rishemjit Kaur</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</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="2105.08321v2-abstract-short" style="display: inline;"> The COVID-19 pandemic has impacted lives and economies across the globe, leading to many deaths. While vaccination is an important intervention, its roll-out is slow and unequal across the globe. Therefore, extensive testing still remains one of the key methods to monitor and contain the virus. Testing on a large scale is expensive and arduous. Hence, we need alternate methods to estimate the numb… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.08321v2-abstract-full').style.display = 'inline'; document.getElementById('2105.08321v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.08321v2-abstract-full" style="display: none;"> The COVID-19 pandemic has impacted lives and economies across the globe, leading to many deaths. While vaccination is an important intervention, its roll-out is slow and unequal across the globe. Therefore, extensive testing still remains one of the key methods to monitor and contain the virus. Testing on a large scale is expensive and arduous. Hence, we need alternate methods to estimate the number of cases. Online surveys have been shown to be an effective method for data collection amidst the pandemic. In this work, we develop machine learning models to estimate the prevalence of COVID-19 using self-reported symptoms. Our best model predicts the daily cases with a mean absolute error (MAE) of 226.30 (normalized MAE of 27.09%) per state, which demonstrates the possibility of predicting the actual number of confirmed cases by utilizing self-reported symptoms. The models are developed at two levels of data granularity - local models, which are trained at the state level, and a single global model which is trained on the combined data aggregated across all states. Our results indicate a lower error on the local models as opposed to the global model. In addition, we also show that the most important symptoms (features) vary considerably from state to state. This work demonstrates that the models developed on crowd-sourced data, curated via online platforms, can complement the existing epidemiological surveillance infrastructure in a cost-effective manner. The code is publicly available at https://github.com/parthpatwa/Can-Self-Reported-Symptoms-Predict-Daily-COVID-19-Cases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.08321v2-abstract-full').style.display = 'none'; document.getElementById('2105.08321v2-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 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted as a full-length oral presentation at the International Workshop on Artificial Intelligence for Social Good (AI4SG), IJCAI-21</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.09174">arXiv:2103.09174</a> <span> [<a href="https://arxiv.org/pdf/2103.09174">pdf</a>, <a href="https://arxiv.org/format/2103.09174">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="Robotics">cs.RO</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/10.1145/3490035.3490263">10.1145/3490035.3490263 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Monocular Multi-Layer Layout Estimation for Warehouse Racks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nigam%2C+M+S">Meher Shashwat Nigam</a>, <a href="/search/cs?searchtype=author&query=Prabhu%2C+A">Avinash Prabhu</a>, <a href="/search/cs?searchtype=author&query=Sahu%2C+A">Anurag Sahu</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+P">Puru Gupta</a>, <a href="/search/cs?searchtype=author&query=Karandikar%2C+T">Tanvi Karandikar</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+N+S">N. Sai Shankar</a>, <a href="/search/cs?searchtype=author&query=Sarvadevabhatla%2C+R+K">Ravi Kiran Sarvadevabhatla</a>, <a href="/search/cs?searchtype=author&query=Krishna%2C+K+M">K. Madhava Krishna</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="2103.09174v3-abstract-short" style="display: inline;"> Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction. To this end, we present RackLay, a deep neural network for real-time shelf layout estimation from a single image. Unlike previous layout estimation methods, which provide a single layout for the dominant ground plane alone, Rac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.09174v3-abstract-full').style.display = 'inline'; document.getElementById('2103.09174v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.09174v3-abstract-full" style="display: none;"> Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction. To this end, we present RackLay, a deep neural network for real-time shelf layout estimation from a single image. Unlike previous layout estimation methods, which provide a single layout for the dominant ground plane alone, RackLay estimates the top-view and front-view layout for each shelf in the considered rack populated with objects. RackLay's architecture and its variants are versatile and estimate accurate layouts for diverse scenes characterized by varying number of visible shelves in an image, large range in shelf occupancy factor and varied background clutter. Given the extreme paucity of datasets in this space and the difficulty involved in acquiring real data from warehouses, we additionally release a flexible synthetic dataset generation pipeline WareSynth which allows users to control the generation process and tailor the dataset according to contingent application. The ablations across architectural variants and comparison with strong prior baselines vindicate the efficacy of RackLay as an apt architecture for the novel problem of multi-layered layout estimation. We also show that fusing the top-view and front-view enables 3D reasoning applications such as metric free space estimation for the considered rack. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.09174v3-abstract-full').style.display = 'none'; document.getElementById('2103.09174v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 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">Visit our project repository at https://github.com/Avinash2468/RackLay</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.09372">arXiv:2102.09372</a> <span> [<a href="https://arxiv.org/pdf/2102.09372">pdf</a>, <a href="https://arxiv.org/format/2102.09372">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Mobile Apps Prioritizing Privacy, Efficiency and Equity: A Decentralized Approach to COVID-19 Vaccination Coordination </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bae%2C+J">Joseph Bae</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Anshuman Sharma</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+I">Ishaan Singh</a>, <a href="/search/cs?searchtype=author&query=Nazir%2C+H">Haris Nazir</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+C">Colin Kang</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+S">Saurish Srivastava</a>, <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Katiyar%2C+P">Priyanshi Katiyar</a>, <a href="/search/cs?searchtype=author&query=Pamplona%2C+V">Vitor Pamplona</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</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="2102.09372v1-abstract-short" style="display: inline;"> In this early draft, we describe a decentralized, app-based approach to COVID-19 vaccine distribution that facilitates zero knowledge verification, dynamic vaccine scheduling, continuous symptoms reporting, access to aggregate analytics based on population trends and more. To ensure equity, our solution is developed to work with limited internet access as well. In addition, we describe the six cri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.09372v1-abstract-full').style.display = 'inline'; document.getElementById('2102.09372v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.09372v1-abstract-full" style="display: none;"> In this early draft, we describe a decentralized, app-based approach to COVID-19 vaccine distribution that facilitates zero knowledge verification, dynamic vaccine scheduling, continuous symptoms reporting, access to aggregate analytics based on population trends and more. To ensure equity, our solution is developed to work with limited internet access as well. In addition, we describe the six critical functions that we believe last mile vaccination management platforms must perform, examine existing vaccine management systems, and present a model for privacy-focused, individual-centric solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.09372v1-abstract-full').style.display = 'none'; document.getElementById('2102.09372v1-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 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.04512">arXiv:2102.04512</a> <span> [<a href="https://arxiv.org/pdf/2102.04512">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Paper card-based vs application-based vaccine credentials: a comparison </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mahindra%2C+A">Aryan Mahindra</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Anshuman Sharma</a>, <a href="/search/cs?searchtype=author&query=Katiyar%2C+P">Priyanshi Katiyar</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+I">Ishaan Singh</a>, <a href="/search/cs?searchtype=author&query=Johnson%2C+A">Albert Johnson</a>, <a href="/search/cs?searchtype=author&query=Jakimowicz%2C+K">Kasia Jakimowicz</a>, <a href="/search/cs?searchtype=author&query=Venkatasubramanian%2C+A">Akarsh Venkatasubramanian</a>, <a href="/search/cs?searchtype=author&query=CV%2C+C">Chandan CV</a>, <a href="/search/cs?searchtype=author&query=Advani%2C+S">Shailesh Advani</a>, <a href="/search/cs?searchtype=author&query=Iyer%2C+R">Rohan Iyer</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+S">Saurish Srivastava</a>, <a href="/search/cs?searchtype=author&query=TV%2C+S">Sethuraman TV</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</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="2102.04512v5-abstract-short" style="display: inline;"> In this early draft, we provide an overview on similarities and differences in the implementation of a paper card-based vaccine credential system and an app-based vaccine credential system. A vaccine credential's primary goal is to regulate entry and ensure safety of individuals within densely packed public locations and workspaces. This is critical for containing the rapid spread of Covid-19 in d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.04512v5-abstract-full').style.display = 'inline'; document.getElementById('2102.04512v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.04512v5-abstract-full" style="display: none;"> In this early draft, we provide an overview on similarities and differences in the implementation of a paper card-based vaccine credential system and an app-based vaccine credential system. A vaccine credential's primary goal is to regulate entry and ensure safety of individuals within densely packed public locations and workspaces. This is critical for containing the rapid spread of Covid-19 in densely packed public locations since a single individual can infect a large majority of people in a crowd. A vaccine credential can also provide information such as an individual's Covid-19 vaccination history and adverse symptom reaction history to judge their potential impact on the overall health of individuals within densely packed public locations and workspaces. After completing the comparisons, we believe a card-based implementation will benefit regions with less socioeconomic mobility, limited resources, and stagnant administrations. An app-based implementation on the other hand will benefit regions with equitable internet access and lower technological divide. We also believe an interoperable system of both credential systems will work best for regions with enormous working-class populations and dense housing clusters. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.04512v5-abstract-full').style.display = 'none'; document.getElementById('2102.04512v5-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 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">10 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/2101.10266">arXiv:2101.10266</a> <span> [<a href="https://arxiv.org/pdf/2101.10266">pdf</a>, <a href="https://arxiv.org/format/2101.10266">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="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> COVID-19 Outbreak Prediction and Analysis using Self Reported Symptoms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=Sethuraman%2C+T+V">T V Sethuraman</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Kanaparti%2C+R">Rishank Kanaparti</a>, <a href="/search/cs?searchtype=author&query=Bae%2C+J">Joseph Bae</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+Y">Yash Mathur</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Chopra%2C+A">Ayush Chopra</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+M">Myungsun Kang</a>, <a href="/search/cs?searchtype=author&query=Ramaswamy%2C+P">Priya Ramaswamy</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</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="2101.10266v2-abstract-short" style="display: inline;"> It is crucial for policymakers to understand the community prevalence of COVID-19 so combative resources can be effectively allocated and prioritized during the COVID-19 pandemic. Traditionally, community prevalence has been assessed through diagnostic and antibody testing data. However, despite the increasing availability of COVID-19 testing, the required level has not been met in most parts of t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.10266v2-abstract-full').style.display = 'inline'; document.getElementById('2101.10266v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.10266v2-abstract-full" style="display: none;"> It is crucial for policymakers to understand the community prevalence of COVID-19 so combative resources can be effectively allocated and prioritized during the COVID-19 pandemic. Traditionally, community prevalence has been assessed through diagnostic and antibody testing data. However, despite the increasing availability of COVID-19 testing, the required level has not been met in most parts of the globe, introducing a need for an alternative method for communities to determine disease prevalence. This is further complicated by the observation that COVID-19 prevalence and spread varies across different spatial, temporal, and demographics. In this study, we understand trends in the spread of COVID-19 by utilizing the results of self-reported COVID-19 symptoms surveys as an alternative to COVID-19 testing reports. This allows us to assess community disease prevalence, even in areas with low COVID-19 testing ability. Using individually reported symptom data from various populations, our method predicts the likely percentage of the population that tested positive for COVID-19. We do so with a Mean Absolute Error (MAE) of 1.14 and Mean Relative Error (MRE) of 60.40\% with 95\% confidence interval as (60.12, 60.67). This implies that our model predicts +/- 1140 cases than the original in a population of 1 million. In addition, we forecast the location-wise percentage of the population testing positive for the next 30 days using self-reported symptoms data from previous days. The MAE for this method is as low as 0.15 (MRE of 23.61\% with 95\% confidence interval as (23.6, 13.7)) for New York. We present an analysis of these results, exposing various clinical attributes of interest across different demographics. Lastly, we qualitatively analyze how various policy enactments (testing, curfew) affect the prevalence of COVID-19 in a community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.10266v2-abstract-full').style.display = 'none'; document.getElementById('2101.10266v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">15 pages, 16 Figures - Latest version on the Journal of Behavioural Data Science - https://isdsa.org/_media/jbds/v1n1/v1n1p8.pdf</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.09847">arXiv:2101.09847</a> <span> [<a href="https://arxiv.org/pdf/2101.09847">pdf</a>, <a href="https://arxiv.org/format/2101.09847">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"> High-Confidence Off-Policy (or Counterfactual) Variance Estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chandak%2C+Y">Yash Chandak</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+P+S">Philip S. Thomas</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="2101.09847v1-abstract-short" style="display: inline;"> Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before deployment, to ensure that the policy will behave as desired. Prior works have studied high-confidence off-policy estimation of the expected return, however, high-con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.09847v1-abstract-full').style.display = 'inline'; document.getElementById('2101.09847v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.09847v1-abstract-full" style="display: none;"> Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before deployment, to ensure that the policy will behave as desired. Prior works have studied high-confidence off-policy estimation of the expected return, however, high-confidence off-policy estimation of the variance of returns can be equally critical for high-risk applications. In this paper, we tackle the previously open problem of estimating and bounding, with high confidence, the variance of returns from off-policy data <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.09847v1-abstract-full').style.display = 'none'; document.getElementById('2101.09847v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">Thirty-fifth AAAI Conference on Artificial Intelligence (AAAI 2021)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.09553">arXiv:2101.09553</a> <span> [<a href="https://arxiv.org/pdf/2101.09553">pdf</a>, <a href="https://arxiv.org/format/2101.09553">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+K">Kevin Black</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shrivu Shankar</a>, <a href="/search/cs?searchtype=author&query=Fonseka%2C+D">Daniel Fonseka</a>, <a href="/search/cs?searchtype=author&query=Deutsch%2C+J">Jacob Deutsch</a>, <a href="/search/cs?searchtype=author&query=Dhir%2C+A">Abhimanyu Dhir</a>, <a href="/search/cs?searchtype=author&query=Akella%2C+M+R">Maruthi R. Akella</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="2101.09553v1-abstract-short" style="display: inline;"> A key requirement for autonomous on-orbit proximity operations is the estimation of a target spacecraft's relative pose (position and orientation). It is desirable to employ monocular cameras for this problem due to their low cost, weight, and power requirements. This work presents a novel convolutional neural network (CNN)-based monocular pose estimation system that achieves state-of-the-art accu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.09553v1-abstract-full').style.display = 'inline'; document.getElementById('2101.09553v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.09553v1-abstract-full" style="display: none;"> A key requirement for autonomous on-orbit proximity operations is the estimation of a target spacecraft's relative pose (position and orientation). It is desirable to employ monocular cameras for this problem due to their low cost, weight, and power requirements. This work presents a novel convolutional neural network (CNN)-based monocular pose estimation system that achieves state-of-the-art accuracy with low computational demand. In combination with a Blender-based synthetic data generation scheme, the system demonstrates the ability to generalize from purely synthetic training data to real in-space imagery of the Northrop Grumman Enhanced Cygnus spacecraft. Additionally, the system achieves real-time performance on low-power flight-like hardware. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.09553v1-abstract-full').style.display = 'none'; document.getElementById('2101.09553v1-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 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Presented at the 31st AAS/AIAA Space Flight Mechanics Meeting, February 2021. 16 pages, 7 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> AAS 21-283 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.07931">arXiv:2101.07931</a> <span> [<a href="https://arxiv.org/pdf/2101.07931">pdf</a>, <a href="https://arxiv.org/format/2101.07931">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> MIT SafePaths Card (MiSaCa): Augmenting Paper Based Vaccination Cards with Printed Codes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bae%2C+J">Joseph Bae</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+S">Saurish Srivastava</a>, <a href="/search/cs?searchtype=author&query=Iyer%2C+R">Rohan Iyer</a>, <a href="/search/cs?searchtype=author&query=Mahindra%2C+A">Aryan Mahindra</a>, <a href="/search/cs?searchtype=author&query=Mirza%2C+Q">Qamil Mirza</a>, <a href="/search/cs?searchtype=author&query=Arseni%2C+M">Maurizio Arseni</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Anshuman Sharma</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+S">Saras Agrawal</a>, <a href="/search/cs?searchtype=author&query=Mukhopadhyay%2C+O">Orna Mukhopadhyay</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+C">Colin Kang</a>, <a href="/search/cs?searchtype=author&query=Katiyar%2C+P">Priyanshi Katiyar</a>, <a href="/search/cs?searchtype=author&query=Shekhar%2C+A">Apurv Shekhar</a>, <a href="/search/cs?searchtype=author&query=Hasan%2C+S">Sifat Hasan</a>, <a href="/search/cs?searchtype=author&query=Dasgupta%2C+K">Krishnendu Dasgupta</a>, <a href="/search/cs?searchtype=author&query=Gandhi%2C+D">Darshan Gandhi</a>, <a href="/search/cs?searchtype=author&query=TV%2C+S">Sethuramen TV</a>, <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+I">Ishaan Singh</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</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="2101.07931v2-abstract-short" style="display: inline;"> In this early draft, we describe a user-centric, card-based system for vaccine distribution. Our system makes use of digitally signed QR codes and their use for phased vaccine distribution, vaccine administration/record-keeping, immunization verification, and follow-up symptom reporting. Furthermore, we propose and describe a complementary scanner app system to be used by vaccination clinics, publ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.07931v2-abstract-full').style.display = 'inline'; document.getElementById('2101.07931v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.07931v2-abstract-full" style="display: none;"> In this early draft, we describe a user-centric, card-based system for vaccine distribution. Our system makes use of digitally signed QR codes and their use for phased vaccine distribution, vaccine administration/record-keeping, immunization verification, and follow-up symptom reporting. Furthermore, we propose and describe a complementary scanner app system to be used by vaccination clinics, public health officials, and immunization verification parties to effectively utilize card-based framework. We believe that the proposed system provides a privacy-preserving and efficient framework for vaccine distribution in both developed and developing regions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.07931v2-abstract-full').style.display = 'none'; document.getElementById('2101.07931v2-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">8 pages, 4 Figures, 1 Table</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.01693">arXiv:2101.01693</a> <span> [<a href="https://arxiv.org/pdf/2101.01693">pdf</a>, <a href="https://arxiv.org/format/2101.01693">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> COVID-19 Tests Gone Rogue: Privacy, Efficacy, Mismanagement and Misunderstandings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Morales%2C+M">Manuel Morales</a>, <a href="/search/cs?searchtype=author&query=Barbar%2C+R">Rachel Barbar</a>, <a href="/search/cs?searchtype=author&query=Gandhi%2C+D">Darshan Gandhi</a>, <a href="/search/cs?searchtype=author&query=Landage%2C+S">Sanskruti Landage</a>, <a href="/search/cs?searchtype=author&query=Bae%2C+J">Joseph Bae</a>, <a href="/search/cs?searchtype=author&query=Vats%2C+A">Arpita Vats</a>, <a href="/search/cs?searchtype=author&query=Kothari%2C+J">Jil Kothari</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+H">Himi Mathur</a>, <a href="/search/cs?searchtype=author&query=Misra%2C+K">Krutika Misra</a>, <a href="/search/cs?searchtype=author&query=Saxena%2C+A">Aishwarya Saxena</a>, <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=V.%2C+S+T">Sethuraman T. V.</a>, <a href="/search/cs?searchtype=author&query=Arseni%2C+M">Maurizio Arseni</a>, <a href="/search/cs?searchtype=author&query=Advani%2C+S">Shailesh Advani</a>, <a href="/search/cs?searchtype=author&query=Jakimowicz%2C+K">Kasia Jakimowicz</a>, <a href="/search/cs?searchtype=author&query=Anand%2C+S">Sunaina Anand</a>, <a href="/search/cs?searchtype=author&query=Katiyar%2C+P">Priyanshi Katiyar</a>, <a href="/search/cs?searchtype=author&query=Mehra%2C+A">Ashley Mehra</a>, <a href="/search/cs?searchtype=author&query=Iyer%2C+R">Rohan Iyer</a>, <a href="/search/cs?searchtype=author&query=Murali%2C+S">Srinidhi Murali</a>, <a href="/search/cs?searchtype=author&query=Mahindra%2C+A">Aryan Mahindra</a>, <a href="/search/cs?searchtype=author&query=Dmitrienko%2C+M">Mikhail Dmitrienko</a>, <a href="/search/cs?searchtype=author&query=Srivastava%2C+S">Saurish Srivastava</a> , et al. (5 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2101.01693v3-abstract-short" style="display: inline;"> COVID-19 testing, the cornerstone for effective screening and identification of COVID-19 cases, remains paramount as an intervention tool to curb the spread of COVID-19 both at local and national levels. However, the speed at which the pandemic struck and the response was rolled out, the widespread impact on healthcare infrastructure, the lack of sufficient preparation within the public health sys… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.01693v3-abstract-full').style.display = 'inline'; document.getElementById('2101.01693v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.01693v3-abstract-full" style="display: none;"> COVID-19 testing, the cornerstone for effective screening and identification of COVID-19 cases, remains paramount as an intervention tool to curb the spread of COVID-19 both at local and national levels. However, the speed at which the pandemic struck and the response was rolled out, the widespread impact on healthcare infrastructure, the lack of sufficient preparation within the public health system, and the complexity of the crisis led to utter confusion among test-takers. Invasion of privacy remains a crucial concern. The user experience of test takers remains low. User friction affects user behavior and discourages participation in testing programs. Test efficacy has been overstated. Test results are poorly understood resulting in inappropriate follow-up recommendations. Herein, we review the current landscape of COVID-19 testing, identify four key challenges, and discuss the consequences of the failure to address these challenges. The current infrastructure around testing and information propagation is highly privacy-invasive and does not leverage scalable digital components. In this work, we discuss challenges complicating the existing covid-19 testing ecosystem and highlight the need to improve the testing experience for the user and reduce privacy invasions. Digital tools will play a critical role in resolving these challenges. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.01693v3-abstract-full').style.display = 'none'; document.getElementById('2101.01693v3-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 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">22 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.00082">arXiv:2101.00082</a> <span> [<a href="https://arxiv.org/pdf/2101.00082">pdf</a>, <a href="https://arxiv.org/format/2101.00082">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"> Bosonic Random Walk Networks for Graph Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Towsley%2C+D">Don Towsley</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="2101.00082v1-abstract-short" style="display: inline;"> The development of Graph Neural Networks (GNNs) has led to great progress in machine learning on graph-structured data. These networks operate via diffusing information across the graph nodes while capturing the structure of the graph. Recently there has also seen tremendous progress in quantum computing techniques. In this work, we explore applications of multi-particle quantum walks on diffusing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.00082v1-abstract-full').style.display = 'inline'; document.getElementById('2101.00082v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.00082v1-abstract-full" style="display: none;"> The development of Graph Neural Networks (GNNs) has led to great progress in machine learning on graph-structured data. These networks operate via diffusing information across the graph nodes while capturing the structure of the graph. Recently there has also seen tremendous progress in quantum computing techniques. In this work, we explore applications of multi-particle quantum walks on diffusing information across graphs. Our model is based on learning the operators that govern the dynamics of quantum random walkers on graphs. We demonstrate the effectiveness of our method on classification and regression tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.00082v1-abstract-full').style.display = 'none'; document.getElementById('2101.00082v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.00074">arXiv:2101.00074</a> <span> [<a href="https://arxiv.org/pdf/2101.00074">pdf</a>, <a href="https://arxiv.org/format/2101.00074">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> </div> </div> <p class="title is-5 mathjax"> Three-quarter Sibling Regression for Denoising Observational Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=Sheldon%2C+D">Daniel Sheldon</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tao Sun</a>, <a href="/search/cs?searchtype=author&query=Pickering%2C+J">John Pickering</a>, <a href="/search/cs?searchtype=author&query=Dietterich%2C+T+G">Thomas G. Dietterich</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="2101.00074v1-abstract-short" style="display: inline;"> Many ecological studies and conservation policies are based on field observations of species, which can be affected by systematic variability introduced by the observation process. A recently introduced causal modeling technique called 'half-sibling regression' can detect and correct for systematic errors in measurements of multiple independent random variables. However, it will remove intrinsic v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.00074v1-abstract-full').style.display = 'inline'; document.getElementById('2101.00074v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.00074v1-abstract-full" style="display: none;"> Many ecological studies and conservation policies are based on field observations of species, which can be affected by systematic variability introduced by the observation process. A recently introduced causal modeling technique called 'half-sibling regression' can detect and correct for systematic errors in measurements of multiple independent random variables. However, it will remove intrinsic variability if the variables are dependent, and therefore does not apply to many situations, including modeling of species counts that are controlled by common causes. We present a technique called 'three-quarter sibling regression' to partially overcome this limitation. It can filter the effect of systematic noise when the latent variables have observed common causes. We provide theoretical justification of this approach, demonstrate its effectiveness on synthetic data, and show that it reduces systematic detection variability due to moon brightness in moth surveys. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.00074v1-abstract-full').style.display = 'none'; document.getElementById('2101.00074v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IJCAI 2019 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.01772">arXiv:2012.01772</a> <span> [<a href="https://arxiv.org/pdf/2012.01772">pdf</a>, <a href="https://arxiv.org/format/2012.01772">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Digital Landscape of COVID-19 Testing: Challenges and Opportunities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gandhi%2C+D">Darshan Gandhi</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Katiyar%2C+P">Priyanshi Katiyar</a>, <a href="/search/cs?searchtype=author&query=Radunsky%2C+A">Alex Radunsky</a>, <a href="/search/cs?searchtype=author&query=Anand%2C+S">Sunaina Anand</a>, <a href="/search/cs?searchtype=author&query=Advani%2C+S">Shailesh Advani</a>, <a href="/search/cs?searchtype=author&query=Kothari%2C+J">Jil Kothari</a>, <a href="/search/cs?searchtype=author&query=Jakimowicz%2C+K">Kasia Jakimowicz</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=V.%2C+S+T">Sethuraman T. V.</a>, <a href="/search/cs?searchtype=author&query=Misra%2C+K">Krutika Misra</a>, <a href="/search/cs?searchtype=author&query=Saxena%2C+A">Aishwarya Saxena</a>, <a href="/search/cs?searchtype=author&query=Landage%2C+S">Sanskruti Landage</a>, <a href="/search/cs?searchtype=author&query=Sonker%2C+R">Richa Sonker</a>, <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=Mahindra%2C+A">Aryan Mahindra</a>, <a href="/search/cs?searchtype=author&query=Dmitrienko%2C+M">Mikhail Dmitrienko</a>, <a href="/search/cs?searchtype=author&query=Vaish%2C+K">Kanishka Vaish</a>, <a href="/search/cs?searchtype=author&query=Mehra%2C+A">Ashley Mehra</a>, <a href="/search/cs?searchtype=author&query=Murali%2C+S">Srinidhi Murali</a>, <a href="/search/cs?searchtype=author&query=Iyer%2C+R">Rohan Iyer</a>, <a href="/search/cs?searchtype=author&query=Bae%2C+J">Joseph Bae</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+V">Vivek Sharma</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=Barbar%2C+R">Rachel Barbar</a> , et al. (1 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2012.01772v1-abstract-short" style="display: inline;"> The COVID-19 Pandemic has left a devastating trail all over the world, in terms of loss of lives, economic decline, travel restrictions, trade deficit, and collapsing economy including real-estate, job loss, loss of health benefits, the decline in quality of access to care and services and overall quality of life. Immunization from the anticipated vaccines will not be the stand-alone guideline tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.01772v1-abstract-full').style.display = 'inline'; document.getElementById('2012.01772v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.01772v1-abstract-full" style="display: none;"> The COVID-19 Pandemic has left a devastating trail all over the world, in terms of loss of lives, economic decline, travel restrictions, trade deficit, and collapsing economy including real-estate, job loss, loss of health benefits, the decline in quality of access to care and services and overall quality of life. Immunization from the anticipated vaccines will not be the stand-alone guideline that will help surpass the pandemic and return to normalcy. Four pillars of effective public health intervention include diagnostic testing for both asymptomatic and symptomatic individuals, contact tracing, quarantine of individuals with symptoms or who are exposed to COVID-19, and maintaining strict hygiene standards at the individual and community level. Digital technology, currently being used for COVID-19 testing include certain mobile apps, web dashboards, and online self-assessment tools. Herein, we look into various digital solutions adapted by communities across universities, businesses, and other organizations. We summarize the challenges experienced using these tools in terms of quality of information, privacy, and user-centric issues. Despite numerous digital solutions available and being developed, many vary in terms of information being shared in terms of both quality and quantity, which can be overwhelming to the users. Understanding the testing landscape through a digital lens will give a clear insight into the multiple challenges that we face including data privacy, cost, and miscommunication. It is the destiny of digitalization to navigate testing for COVID-19. Block-chain based systems can be used for privacy preservation and ensuring ownership of the data to remain with the user. Another solution involves having digital health passports with relevant and correct information. In this early draft, we summarize the challenges and propose possible solutions to address the same. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.01772v1-abstract-full').style.display = 'none'; document.getElementById('2012.01772v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">28 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/2010.11645">arXiv:2010.11645</a> <span> [<a href="https://arxiv.org/pdf/2010.11645">pdf</a>, <a href="https://arxiv.org/format/2010.11645">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> </div> </div> <p class="title is-5 mathjax"> Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dathathri%2C+S">Sumanth Dathathri</a>, <a href="/search/cs?searchtype=author&query=Dvijotham%2C+K">Krishnamurthy Dvijotham</a>, <a href="/search/cs?searchtype=author&query=Kurakin%2C+A">Alexey Kurakin</a>, <a href="/search/cs?searchtype=author&query=Raghunathan%2C+A">Aditi Raghunathan</a>, <a href="/search/cs?searchtype=author&query=Uesato%2C+J">Jonathan Uesato</a>, <a href="/search/cs?searchtype=author&query=Bunel%2C+R">Rudy Bunel</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Steinhardt%2C+J">Jacob Steinhardt</a>, <a href="/search/cs?searchtype=author&query=Goodfellow%2C+I">Ian Goodfellow</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+P">Percy Liang</a>, <a href="/search/cs?searchtype=author&query=Kohli%2C+P">Pushmeet Kohli</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="2010.11645v2-abstract-short" style="display: inline;"> Convex relaxations have emerged as a promising approach for verifying desirable properties of neural networks like robustness to adversarial perturbations. Widely used Linear Programming (LP) relaxations only work well when networks are trained to facilitate verification. This precludes applications that involve verification-agnostic networks, i.e., networks not specially trained for verification.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.11645v2-abstract-full').style.display = 'inline'; document.getElementById('2010.11645v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.11645v2-abstract-full" style="display: none;"> Convex relaxations have emerged as a promising approach for verifying desirable properties of neural networks like robustness to adversarial perturbations. Widely used Linear Programming (LP) relaxations only work well when networks are trained to facilitate verification. This precludes applications that involve verification-agnostic networks, i.e., networks not specially trained for verification. On the other hand, semidefinite programming (SDP) relaxations have successfully be applied to verification-agnostic networks, but do not currently scale beyond small networks due to poor time and space asymptotics. In this work, we propose a first-order dual SDP algorithm that (1) requires memory only linear in the total number of network activations, (2) only requires a fixed number of forward/backward passes through the network per iteration. By exploiting iterative eigenvector methods, we express all solver operations in terms of forward and backward passes through the network, enabling efficient use of hardware like GPUs/TPUs. For two verification-agnostic networks on MNIST and CIFAR-10, we significantly improve L-inf verified robust accuracy from 1% to 88% and 6% to 40% respectively. We also demonstrate tight verification of a quadratic stability specification for the decoder of a variational autoencoder. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.11645v2-abstract-full').style.display = 'none'; document.getElementById('2010.11645v2-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 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.04991">arXiv:2009.04991</a> <span> [<a href="https://arxiv.org/pdf/2009.04991">pdf</a>, <a href="https://arxiv.org/ps/2009.04991">ps</a>, <a href="https://arxiv.org/format/2009.04991">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</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"> Proximity Sensing: Modeling and Understanding Noisy RSSI-BLE Signals and Other Mobile Sensor Data for Digital Contact Tracing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Sheshank Shankar</a>, <a href="/search/cs?searchtype=author&query=Kanaparti%2C+R">Rishank Kanaparti</a>, <a href="/search/cs?searchtype=author&query=Chopra%2C+A">Ayush Chopra</a>, <a href="/search/cs?searchtype=author&query=Sukumaran%2C+R">Rohan Sukumaran</a>, <a href="/search/cs?searchtype=author&query=Patwa%2C+P">Parth Patwa</a>, <a href="/search/cs?searchtype=author&query=Kang%2C+M">Myungsun Kang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Abhishek Singh</a>, <a href="/search/cs?searchtype=author&query=McPherson%2C+K+P">Kevin P. McPherson</a>, <a href="/search/cs?searchtype=author&query=Raskar%2C+R">Ramesh Raskar</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="2009.04991v3-abstract-short" style="display: inline;"> As we await a vaccine, social-distancing via efficient contact tracing has emerged as the primary health strategy to dampen the spread of COVID-19. To enable efficient digital contact tracing, we present a novel system to estimate pair-wise individual proximity, via a joint model of Bluetooth Low Energy (BLE) signals with other on-device sensors (accelerometer, magnetometer, gyroscope). We explore… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.04991v3-abstract-full').style.display = 'inline'; document.getElementById('2009.04991v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.04991v3-abstract-full" style="display: none;"> As we await a vaccine, social-distancing via efficient contact tracing has emerged as the primary health strategy to dampen the spread of COVID-19. To enable efficient digital contact tracing, we present a novel system to estimate pair-wise individual proximity, via a joint model of Bluetooth Low Energy (BLE) signals with other on-device sensors (accelerometer, magnetometer, gyroscope). We explore multiple ways of interpreting the sensor data stream (time-series, histogram, etc) and use several statistical and deep learning methods to learn representations for sensing proximity. We report the normalized Decision Cost Function (nDCF) metric and analyze the differential impact of the various input signals, as well as discuss various challenges associated with this task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.04991v3-abstract-full').style.display = 'none'; document.getElementById('2009.04991v3-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 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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">Accepted to IEEE/ICACT' 2021: International Conference on Advanced Communication Technology. Also presented at the Machine Learning for Mobile Health workshop at NeurIPS 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.04662">arXiv:2007.04662</a> <span> [<a href="https://arxiv.org/pdf/2007.04662">pdf</a>, <a href="https://arxiv.org/format/2007.04662">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"> Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Piratla%2C+V">Vihari Piratla</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</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="2007.04662v1-abstract-short" style="display: inline;"> Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared between the original and augmented counterparts. However, we show that is not the case even for the best augmentation technique. In this work, we take a Domain Gen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.04662v1-abstract-full').style.display = 'inline'; document.getElementById('2007.04662v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.04662v1-abstract-full" style="display: none;"> Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared between the original and augmented counterparts. However, we show that is not the case even for the best augmentation technique. In this work, we take a Domain Generalization viewpoint of augmentation based methods. This new perspective allowed for probing overfitting and delineating avenues for improvement. Our exploration with the state-of-art augmentation method provides evidence that the learned representations are not as robust even towards distortions used during training. This suggests evidence for the untapped potential of augmented examples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.04662v1-abstract-full').style.display = 'none'; document.getElementById('2007.04662v1-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 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">6 pages, ICML 2020 Workshop on Uncertainty and Ro-bustness in Deep Learning</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.03512">arXiv:2006.03512</a> <span> [<a href="https://arxiv.org/pdf/2006.03512">pdf</a>, <a href="https://arxiv.org/format/2006.03512">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> MRFMap: Online Probabilistic 3D Mapping using Forward Ray Sensor Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+K+S">Kumar Shaurya Shankar</a>, <a href="/search/cs?searchtype=author&query=Michael%2C+N">Nathan Michael</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="2006.03512v2-abstract-short" style="display: inline;"> Traditional dense volumetric representations for robotic mapping make simplifying assumptions about sensor noise characteristics due to computational constraints. We present a framework that, unlike conventional occupancy grid maps, explicitly models the sensor ray formation for a depth sensor via a Markov Random Field and performs loopy belief propagation to infer the marginal probability of occu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.03512v2-abstract-full').style.display = 'inline'; document.getElementById('2006.03512v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.03512v2-abstract-full" style="display: none;"> Traditional dense volumetric representations for robotic mapping make simplifying assumptions about sensor noise characteristics due to computational constraints. We present a framework that, unlike conventional occupancy grid maps, explicitly models the sensor ray formation for a depth sensor via a Markov Random Field and performs loopy belief propagation to infer the marginal probability of occupancy at each voxel in a map. By explicitly reasoning about occlusions our approach models the correlations between adjacent voxels in the map. Further, by incorporating learnt sensor noise characteristics we perform accurate inference even with noisy sensor data without ad-hoc definitions of sensor uncertainty. We propose a new metric for evaluating probabilistic volumetric maps and demonstrate the higher fidelity of our approach on simulated as well as real-world datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.03512v2-abstract-full').style.display = 'none'; document.getElementById('2006.03512v2-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">Paper to be published at RSS 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.02487">arXiv:2006.02487</a> <span> [<a href="https://arxiv.org/pdf/2006.02487">pdf</a>, <a href="https://arxiv.org/format/2006.02487">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> Visualizing Webpage Changes Over Time </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mabe%2C+A">Abigail Mabe</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+D">Dhruv Patel</a>, <a href="/search/cs?searchtype=author&query=Gunnam%2C+M">Maheedhar Gunnam</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Surbhi Shankar</a>, <a href="/search/cs?searchtype=author&query=Kelly%2C+M">Mat Kelly</a>, <a href="/search/cs?searchtype=author&query=Alam%2C+S">Sawood Alam</a>, <a href="/search/cs?searchtype=author&query=Nelson%2C+M+L">Michael L. Nelson</a>, <a href="/search/cs?searchtype=author&query=Weigle%2C+M+C">Michele C. Weigle</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="2006.02487v1-abstract-short" style="display: inline;"> We report on the development of TMVis, a web service to provide visualizations of how individual webpages have changed over time. We leverage past research on summarizing collections of webpages with thumbnail-sized screenshots and on choosing a small number of representative past archived webpages from a large collection. We offer four visualizations: image grid, image slider, timeline, and anima… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.02487v1-abstract-full').style.display = 'inline'; document.getElementById('2006.02487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.02487v1-abstract-full" style="display: none;"> We report on the development of TMVis, a web service to provide visualizations of how individual webpages have changed over time. We leverage past research on summarizing collections of webpages with thumbnail-sized screenshots and on choosing a small number of representative past archived webpages from a large collection. We offer four visualizations: image grid, image slider, timeline, and animated GIF. Embed codes for the image grid and image slider can be produced to include these on separate webpages. The animated GIF can be downloaded as an image file for the same purpose. This tool can be used to allow scholars from various disciplines, as well as the general public, to explore the temporal nature of web archives. We hope that these visualizations will just be the beginning and will provide a starting point for others to expand these types of offerings for users of web archives. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.02487v1-abstract-full').style.display = 'none'; document.getElementById('2006.02487v1-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">13 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.08158">arXiv:2005.08158</a> <span> [<a href="https://arxiv.org/pdf/2005.08158">pdf</a>, <a href="https://arxiv.org/format/2005.08158">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"> Optimizing for the Future in Non-Stationary MDPs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chandak%2C+Y">Yash Chandak</a>, <a href="/search/cs?searchtype=author&query=Theocharous%2C+G">Georgios Theocharous</a>, <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shiv Shankar</a>, <a href="/search/cs?searchtype=author&query=White%2C+M">Martha White</a>, <a href="/search/cs?searchtype=author&query=Mahadevan%2C+S">Sridhar Mahadevan</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+P+S">Philip S. Thomas</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="2005.08158v4-abstract-short" style="display: inline;"> Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this assumption is violated, and using existing algorithms may result in a performance lag. To proactively search for a good future policy, we present a policy grad… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.08158v4-abstract-full').style.display = 'inline'; document.getElementById('2005.08158v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.08158v4-abstract-full" style="display: none;"> Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this assumption is violated, and using existing algorithms may result in a performance lag. To proactively search for a good future policy, we present a policy gradient algorithm that maximizes a forecast of future performance. This forecast is obtained by fitting a curve to the counter-factual estimates of policy performance over time, without explicitly modeling the underlying non-stationarity. The resulting algorithm amounts to a non-uniform reweighting of past data, and we observe that minimizing performance over some of the data from past episodes can be beneficial when searching for a policy that maximizes future performance. We show that our algorithm, called Prognosticator, is more robust to non-stationarity than two online adaptation techniques, on three simulated problems motivated by real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.08158v4-abstract-full').style.display = 'none'; document.getElementById('2005.08158v4-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 September, 2020; <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">Thirty-seventh International Conference on Machine Learning (ICML 2020)</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=Shankar%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Shankar%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Shankar%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