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 1–13 of 13 results for author: <span class="mathjax">Daniel, C</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=Daniel%2C+C">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="Daniel, C"> </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=Daniel%2C+C&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="Daniel, C"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.14066">arXiv:2406.14066</a> <span> [<a href="https://arxiv.org/pdf/2406.14066">pdf</a>, <a href="https://arxiv.org/format/2406.14066">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="Performance">cs.PF</span> </div> </div> <p class="title is-5 mathjax"> Optimizing Speculative Decoding for Serving Large Language Models Using Goodput </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xiaoxuan Liu</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Cade Daniel</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+L">Langxiang Hu</a>, <a href="/search/cs?searchtype=author&query=Kwon%2C+W">Woosuk Kwon</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zhuohan Li</a>, <a href="/search/cs?searchtype=author&query=Mo%2C+X">Xiangxi Mo</a>, <a href="/search/cs?searchtype=author&query=Cheung%2C+A">Alvin Cheung</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Z">Zhijie Deng</a>, <a href="/search/cs?searchtype=author&query=Stoica%2C+I">Ion Stoica</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hao Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.14066v2-abstract-short" style="display: inline;"> Reducing the inference latency of large language models (LLMs) is crucial, and speculative decoding (SD) stands out as one of the most effective techniques. Rather than letting the LLM generate all tokens directly, speculative decoding employs effective proxies to predict potential outputs, which are then verified by the LLM without compromising the generation quality. Yet, deploying SD in real on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14066v2-abstract-full').style.display = 'inline'; document.getElementById('2406.14066v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.14066v2-abstract-full" style="display: none;"> Reducing the inference latency of large language models (LLMs) is crucial, and speculative decoding (SD) stands out as one of the most effective techniques. Rather than letting the LLM generate all tokens directly, speculative decoding employs effective proxies to predict potential outputs, which are then verified by the LLM without compromising the generation quality. Yet, deploying SD in real online LLM serving systems (with continuous batching) does not always yield improvement -- under higher request rates or low speculation accuracy, it paradoxically increases latency. Furthermore, there is no best speculation length work for all workloads under different system loads. Based on the observations, we develop a dynamic framework SmartSpec. SmartSpec dynamically determines the best speculation length for each request (from 0, i.e., no speculation, to many tokens) -- hence the associated speculative execution costs -- based on a new metric called goodput, which characterizes the current observed load of the entire system and the speculation accuracy. We show that SmartSpec consistently reduces average request latency by up to 3.2x compared to non-speculative decoding baselines across different sizes of target models, draft models, request rates, and datasets. Moreover, SmartSpec can be applied to different styles of speculative decoding, including traditional, model-based approaches as well as model-free methods like prompt lookup and tree-style decoding. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14066v2-abstract-full').style.display = 'none'; document.getElementById('2406.14066v2-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">v1</span> submitted 20 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.10327">arXiv:2403.10327</a> <span> [<a href="https://arxiv.org/pdf/2403.10327">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <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"> Unsupervised Threat Hunting using Continuous Bag-of-Terms-and-Time (CBoTT) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kayhan%2C+V">Varol Kayhan</a>, <a href="/search/cs?searchtype=author&query=Shivendu%2C+S">Shivendu Shivendu</a>, <a href="/search/cs?searchtype=author&query=Behnia%2C+R">Rouzbeh Behnia</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Clinton Daniel</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+M">Manish Agrawal</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="2403.10327v1-abstract-short" style="display: inline;"> Threat hunting is sifting through system logs to detect malicious activities that might have bypassed existing security measures. It can be performed in several ways, one of which is based on detecting anomalies. We propose an unsupervised framework, called continuous bag-of-terms-and-time (CBoTT), and publish its application programming interface (API) to help researchers and cybersecurity analys… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10327v1-abstract-full').style.display = 'inline'; document.getElementById('2403.10327v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.10327v1-abstract-full" style="display: none;"> Threat hunting is sifting through system logs to detect malicious activities that might have bypassed existing security measures. It can be performed in several ways, one of which is based on detecting anomalies. We propose an unsupervised framework, called continuous bag-of-terms-and-time (CBoTT), and publish its application programming interface (API) to help researchers and cybersecurity analysts perform anomaly-based threat hunting among SIEM logs geared toward process auditing on endpoint devices. Analyses show that our framework consistently outperforms benchmark approaches. When logs are sorted by likelihood of being an anomaly (from most likely to least), our approach identifies anomalies at higher percentiles (between 1.82-6.46) while benchmark approaches identify the same anomalies at lower percentiles (between 3.25-80.92). This framework can be used by other researchers to conduct benchmark analyses and cybersecurity analysts to find anomalies in SIEM logs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10327v1-abstract-full').style.display = 'none'; document.getElementById('2403.10327v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.05972">arXiv:2111.05972</a> <span> [<a href="https://arxiv.org/pdf/2111.05972">pdf</a>, <a href="https://arxiv.org/format/2111.05972">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Karakus%2C+C">Can Karakus</a>, <a href="/search/cs?searchtype=author&query=Huilgol%2C+R">Rahul Huilgol</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+F">Fei Wu</a>, <a href="/search/cs?searchtype=author&query=Subramanian%2C+A">Anirudh Subramanian</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Cade Daniel</a>, <a href="/search/cs?searchtype=author&query=Cavdar%2C+D">Derya Cavdar</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+T">Teng Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Haohan Chen</a>, <a href="/search/cs?searchtype=author&query=Rahnama%2C+A">Arash Rahnama</a>, <a href="/search/cs?searchtype=author&query=Quintela%2C+L">Luis Quintela</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.05972v1-abstract-short" style="display: inline;"> With deep learning models rapidly growing in size, systems-level solutions for large-model training are required. We present Amazon SageMaker model parallelism, a software library that integrates with PyTorch, and enables easy training of large models using model parallelism and other memory-saving features. In contrast to existing solutions, the implementation of the SageMaker library is much mor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.05972v1-abstract-full').style.display = 'inline'; document.getElementById('2111.05972v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.05972v1-abstract-full" style="display: none;"> With deep learning models rapidly growing in size, systems-level solutions for large-model training are required. We present Amazon SageMaker model parallelism, a software library that integrates with PyTorch, and enables easy training of large models using model parallelism and other memory-saving features. In contrast to existing solutions, the implementation of the SageMaker library is much more generic and flexible, in that it can automatically partition and run pipeline parallelism over arbitrary model architectures with minimal code change, and also offers a general and extensible framework for tensor parallelism, which supports a wider range of use cases, and is modular enough to be easily applied to new training scripts. The library also preserves the native PyTorch user experience to a much larger degree, supporting module re-use and dynamic graphs, while giving the user full control over the details of the training step. We evaluate performance over GPT-3, RoBERTa, BERT, and neural collaborative filtering, and demonstrate competitive performance over existing solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.05972v1-abstract-full').style.display = 'none'; document.getElementById('2111.05972v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">24 pages. Submitted for review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.07459">arXiv:2109.07459</a> <span> [<a href="https://arxiv.org/pdf/2109.07459">pdf</a>, <a href="https://arxiv.org/ps/2109.07459">ps</a>, <a href="https://arxiv.org/format/2109.07459">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</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"> Timely Updating with Intermittent Energy and Data for Multiple Sources over Erasure Channels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christopher Daniel Jr.</a>, <a href="/search/cs?searchtype=author&query=Arafa%2C+A">Ahmed Arafa</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.07459v1-abstract-short" style="display: inline;"> A status updating system is considered in which multiple data sources generate packets to be delivered to a destination through a shared energy harvesting sensor. Only one source's data, when available, can be transmitted by the sensor at a time, subject to energy availability. Transmissions are prune to erasures, and each successful transmission constitutes a status update for its corresponding s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.07459v1-abstract-full').style.display = 'inline'; document.getElementById('2109.07459v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.07459v1-abstract-full" style="display: none;"> A status updating system is considered in which multiple data sources generate packets to be delivered to a destination through a shared energy harvesting sensor. Only one source's data, when available, can be transmitted by the sensor at a time, subject to energy availability. Transmissions are prune to erasures, and each successful transmission constitutes a status update for its corresponding source at the destination. The goal is to schedule source transmissions such that the collective long-term average age-of-information (AoI) is minimized. AoI is defined as the time elapsed since the latest successfully-received data has been generated at its source. To solve this problem, the case with a single source is first considered, with a focus on threshold waiting policies, in which the sensor attempts transmission only if the time until both energy and data are available grows above a certain threshold. The distribution of the AoI is fully characterized under such a policy. This is then used to analyze the performance of the multiple sources case under maximum-age-first scheduling, in which the sensor's resources are dedicated to the source with the maximum AoI at any given time. The achievable collective long-term average AoI is derived in closed-form. Multiple numerical evaluations are demonstrated to show how the optimal threshold value behaves as a function of the system parameters, and showcase the benefits of a threshold-based waiting policy with intermittent energy and data arrivals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.07459v1-abstract-full').style.display = 'none'; document.getElementById('2109.07459v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Appeared in the International Symposium on Wireless Communication Systems (ISWCS) 2021, special session on Age of Information</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.12346">arXiv:2108.12346</a> <span> [<a href="https://arxiv.org/pdf/2108.12346">pdf</a>, <a href="https://arxiv.org/format/2108.12346">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 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/10.1145/3480136">10.1145/3480136 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Perceptually-Validated Metric for Crowd Trajectory Quality Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Daniel%2C+B+C">Beatriz Cabrero Daniel</a>, <a href="/search/cs?searchtype=author&query=Marques%2C+R">Ricardo Marques</a>, <a href="/search/cs?searchtype=author&query=Hoyet%2C+L">Ludovic Hoyet</a>, <a href="/search/cs?searchtype=author&query=Pettr%C3%A9%2C+J">Julien Pettr茅</a>, <a href="/search/cs?searchtype=author&query=Blat%2C+J">Josep Blat</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="2108.12346v3-abstract-short" style="display: inline;"> Simulating crowds requires controlling a very large number of trajectories and is usually performed using crowd motion algorithms for which appropriate parameter values need to be found. The study of the relation between parametric values for simulation techniques and the quality of the resulting trajectories has been studied either through perceptual experiments or by comparison with real crowd t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12346v3-abstract-full').style.display = 'inline'; document.getElementById('2108.12346v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.12346v3-abstract-full" style="display: none;"> Simulating crowds requires controlling a very large number of trajectories and is usually performed using crowd motion algorithms for which appropriate parameter values need to be found. The study of the relation between parametric values for simulation techniques and the quality of the resulting trajectories has been studied either through perceptual experiments or by comparison with real crowd trajectories. In this paper, we integrate both strategies. A quality metric, QF, is proposed to abstract from reference data while capturing the most salient features that affect the perception of trajectory realism. QF weights and combines cost functions that are based on several individual, local and global properties of trajectories. These trajectory features are selected from the literature and from interviews with experts. To validate the capacity of QF to capture perceived trajectory quality, we conduct an online experiment that demonstrates the high agreement between the automatic quality score and non-expert users. To further demonstrate the usefulness of QF, we use it in a data-free parameter tuning application able to tune any parametric microscopic crowd simulation model that outputs independent trajectories for characters. The learnt parameters for the tuned crowd motion model maintain the influence of the reference data which was used to weight the terms of QF. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12346v3-abstract-full').style.display = 'none'; document.getElementById('2108.12346v3-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 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">17 pages, to appear on PACMGIT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.01646">arXiv:2104.01646</a> <span> [<a href="https://arxiv.org/pdf/2104.01646">pdf</a>, <a href="https://arxiv.org/format/2104.01646">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> SOLO: Search Online, Learn Offline for Combinatorial Optimization Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Oren%2C+J">Joel Oren</a>, <a href="/search/cs?searchtype=author&query=Ross%2C+C">Chana Ross</a>, <a href="/search/cs?searchtype=author&query=Lefarov%2C+M">Maksym Lefarov</a>, <a href="/search/cs?searchtype=author&query=Richter%2C+F">Felix Richter</a>, <a href="/search/cs?searchtype=author&query=Taitler%2C+A">Ayal Taitler</a>, <a href="/search/cs?searchtype=author&query=Feldman%2C+Z">Zohar Feldman</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christian Daniel</a>, <a href="/search/cs?searchtype=author&query=Di+Castro%2C+D">Dotan Di Castro</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="2104.01646v3-abstract-short" style="display: inline;"> We study combinatorial problems with real world applications such as machine scheduling, routing, and assignment. We propose a method that combines Reinforcement Learning (RL) and planning. This method can equally be applied to both the offline, as well as online, variants of the combinatorial problem, in which the problem components (e.g., jobs in scheduling problems) are not known in advance, bu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.01646v3-abstract-full').style.display = 'inline'; document.getElementById('2104.01646v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.01646v3-abstract-full" style="display: none;"> We study combinatorial problems with real world applications such as machine scheduling, routing, and assignment. We propose a method that combines Reinforcement Learning (RL) and planning. This method can equally be applied to both the offline, as well as online, variants of the combinatorial problem, in which the problem components (e.g., jobs in scheduling problems) are not known in advance, but rather arrive during the decision-making process. Our solution is quite generic, scalable, and leverages distributional knowledge of the problem parameters. We frame the solution process as an MDP, and take a Deep Q-Learning approach wherein states are represented as graphs, thereby allowing our trained policies to deal with arbitrary changes in a principled manner. Though learned policies work well in expectation, small deviations can have substantial negative effects in combinatorial settings. We mitigate these drawbacks by employing our graph-convolutional policies as non-optimal heuristics in a compatible search algorithm, Monte Carlo Tree Search, to significantly improve overall performance. We demonstrate our method on two problems: Machine Scheduling and Capacitated Vehicle Routing. We show that our method outperforms custom-tailored mathematical solvers, state of the art learning-based algorithms, and common heuristics, both in computation time and performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.01646v3-abstract-full').style.display = 'none'; document.getElementById('2104.01646v3-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 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.09301">arXiv:2002.09301</a> <span> [<a href="https://arxiv.org/pdf/2002.09301">pdf</a>, <a href="https://arxiv.org/format/2002.09301">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kersting%2C+H">Hans Kersting</a>, <a href="/search/cs?searchtype=author&query=Kr%C3%A4mer%2C+N">Nicholas Kr盲mer</a>, <a href="/search/cs?searchtype=author&query=Schiegg%2C+M">Martin Schiegg</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christian Daniel</a>, <a href="/search/cs?searchtype=author&query=Tiemann%2C+M">Michael Tiemann</a>, <a href="/search/cs?searchtype=author&query=Hennig%2C+P">Philipp Hennig</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2002.09301v2-abstract-short" style="display: inline;"> Likelihood-free (a.k.a. simulation-based) inference problems are inverse problems with expensive, or intractable, forward models. ODE inverse problems are commonly treated as likelihood-free, as their forward map has to be numerically approximated by an ODE solver. This, however, is not a fundamental constraint but just a lack of functionality in classic ODE solvers, which do not return a likeliho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.09301v2-abstract-full').style.display = 'inline'; document.getElementById('2002.09301v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.09301v2-abstract-full" style="display: none;"> Likelihood-free (a.k.a. simulation-based) inference problems are inverse problems with expensive, or intractable, forward models. ODE inverse problems are commonly treated as likelihood-free, as their forward map has to be numerically approximated by an ODE solver. This, however, is not a fundamental constraint but just a lack of functionality in classic ODE solvers, which do not return a likelihood but a point estimate. To address this shortcoming, we employ Gaussian ODE filtering (a probabilistic numerical method for ODEs) to construct a local Gaussian approximation to the likelihood. This approximation yields tractable estimators for the gradient and Hessian of the (log-)likelihood. Insertion of these estimators into existing gradient-based optimization and sampling methods engenders new solvers for ODE inverse problems. We demonstrate that these methods outperform standard likelihood-free approaches on three benchmark-systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.09301v2-abstract-full').style.display = 'none'; document.getElementById('2002.09301v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">11 pages (+ 5 pages appendix), 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> Published at ICML 2020 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.02820">arXiv:2002.02820</a> <span> [<a href="https://arxiv.org/pdf/2002.02820">pdf</a>, <a href="https://arxiv.org/format/2002.02820">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Noisy-Input Entropy Search for Efficient Robust Bayesian Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fr%C3%B6hlich%2C+L+P">Lukas P. Fr枚hlich</a>, <a href="/search/cs?searchtype=author&query=Klenske%2C+E+D">Edgar D. Klenske</a>, <a href="/search/cs?searchtype=author&query=Vinogradska%2C+J">Julia Vinogradska</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christian Daniel</a>, <a href="/search/cs?searchtype=author&query=Zeilinger%2C+M+N">Melanie N. Zeilinger</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2002.02820v1-abstract-short" style="display: inline;"> We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input Entropy Search (NES), a novel information-theoretic acquisition function that is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.02820v1-abstract-full').style.display = 'inline'; document.getElementById('2002.02820v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.02820v1-abstract-full" style="display: none;"> We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input Entropy Search (NES), a novel information-theoretic acquisition function that is designed to find robust optima for problems with both input and measurement noise. NES is based on the key insight that the robust objective in many cases can be modeled as a Gaussian process, however, it cannot be observed directly. We evaluate NES on several benchmark problems from the optimization literature and from engineering. The results show that NES reliably finds robust optima, outperforming existing methods from the literature on all benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.02820v1-abstract-full').style.display = 'none'; document.getElementById('2002.02820v1-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 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2001.07394">arXiv:2001.07394</a> <span> [<a href="https://arxiv.org/pdf/2001.07394">pdf</a>, <a href="https://arxiv.org/format/2001.07394">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Bayesian Optimization for Policy Search in High-Dimensional Systems via Automatic Domain Selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fr%C3%B6hlich%2C+L+P">Lukas P. Fr枚hlich</a>, <a href="/search/cs?searchtype=author&query=Klenske%2C+E+D">Edgar D. Klenske</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C+G">Christian G. Daniel</a>, <a href="/search/cs?searchtype=author&query=Zeilinger%2C+M+N">Melanie N. Zeilinger</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="2001.07394v1-abstract-short" style="display: inline;"> Bayesian Optimization (BO) is an effective method for optimizing expensive-to-evaluate black-box functions with a wide range of applications for example in robotics, system design and parameter optimization. However, scaling BO to problems with large input dimensions (>10) remains an open challenge. In this paper, we propose to leverage results from optimal control to scale BO to higher dimensiona… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.07394v1-abstract-full').style.display = 'inline'; document.getElementById('2001.07394v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2001.07394v1-abstract-full" style="display: none;"> Bayesian Optimization (BO) is an effective method for optimizing expensive-to-evaluate black-box functions with a wide range of applications for example in robotics, system design and parameter optimization. However, scaling BO to problems with large input dimensions (>10) remains an open challenge. In this paper, we propose to leverage results from optimal control to scale BO to higher dimensional control tasks and to reduce the need for manually selecting the optimization domain. The contributions of this paper are twofold: 1) We show how we can make use of a learned dynamics model in combination with a model-based controller to simplify the BO problem by focusing onto the most relevant regions of the optimization domain. 2) Based on (1) we present a method to find an embedding in parameter space that reduces the effective dimensionality of the optimization problem. To evaluate the effectiveness of the proposed approach, we present an experimental evaluation on real hardware, as well as simulated tasks including a 48-dimensional policy for a quadcopter. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.07394v1-abstract-full').style.display = 'none'; document.getElementById('2001.07394v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.05727">arXiv:1911.05727</a> <span> [<a href="https://arxiv.org/pdf/1911.05727">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="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Artificial Intelligence Strategies for National Security and Safety Standards </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Blasch%2C+E">Erik Blasch</a>, <a href="/search/cs?searchtype=author&query=Sung%2C+J">James Sung</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tao Nguyen</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C+P">Chandra P. Daniel</a>, <a href="/search/cs?searchtype=author&query=Mason%2C+A+P">Alisa P. Mason</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="1911.05727v1-abstract-short" style="display: inline;"> Recent advances in artificial intelligence (AI) have lead to an explosion of multimedia applications (e.g., computer vision (CV) and natural language processing (NLP)) for different domains such as commercial, industrial, and intelligence. In particular, the use of AI applications in a national security environment is often problematic because the opaque nature of the systems leads to an inability… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.05727v1-abstract-full').style.display = 'inline'; document.getElementById('1911.05727v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.05727v1-abstract-full" style="display: none;"> Recent advances in artificial intelligence (AI) have lead to an explosion of multimedia applications (e.g., computer vision (CV) and natural language processing (NLP)) for different domains such as commercial, industrial, and intelligence. In particular, the use of AI applications in a national security environment is often problematic because the opaque nature of the systems leads to an inability for a human to understand how the results came about. A reliance on 'black boxes' to generate predictions and inform decisions is potentially disastrous. This paper explores how the application of standards during each stage of the development of an AI system deployed and used in a national security environment would help enable trust. Specifically, we focus on the standards outlined in Intelligence Community Directive 203 (Analytic Standards) to subject machine outputs to the same rigorous standards as analysis performed by humans. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.05727v1-abstract-full').style.display = 'none'; document.getElementById('1911.05727v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Presented at AAAI FSS-19: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.05710">arXiv:1905.05710</a> <span> [<a href="https://arxiv.org/pdf/1905.05710">pdf</a>, <a href="https://arxiv.org/format/1905.05710">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"> Trajectory-Based Off-Policy Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Doerr%2C+A">Andreas Doerr</a>, <a href="/search/cs?searchtype=author&query=Volpp%2C+M">Michael Volpp</a>, <a href="/search/cs?searchtype=author&query=Toussaint%2C+M">Marc Toussaint</a>, <a href="/search/cs?searchtype=author&query=Trimpe%2C+S">Sebastian Trimpe</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christian Daniel</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="1905.05710v1-abstract-short" style="display: inline;"> Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weaknesses by combining recent improvements in the reuse of off-policy data and exploration in parameter s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.05710v1-abstract-full').style.display = 'inline'; document.getElementById('1905.05710v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.05710v1-abstract-full" style="display: none;"> Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weaknesses by combining recent improvements in the reuse of off-policy data and exploration in parameter space with deterministic behavioral policies. The resulting objective is amenable to standard neural network optimization strategies like stochastic gradient descent or stochastic gradient Hamiltonian Monte Carlo. Incorporation of previous rollouts via importance sampling greatly improves data-efficiency, whilst stochastic optimization schemes facilitate the escape from local optima. We evaluate the proposed approach on a series of continuous control benchmark tasks. The results show that the proposed algorithm is able to successfully and reliably learn solutions using fewer system interactions than standard policy gradient methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.05710v1-abstract-full').style.display = 'none'; document.getElementById('1905.05710v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Includes appendix. Accepted for ICML 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.02642">arXiv:1904.02642</a> <span> [<a href="https://arxiv.org/pdf/1904.02642">pdf</a>, <a href="https://arxiv.org/format/1904.02642">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Volpp%2C+M">Michael Volpp</a>, <a href="/search/cs?searchtype=author&query=Fr%C3%B6hlich%2C+L+P">Lukas P. Fr枚hlich</a>, <a href="/search/cs?searchtype=author&query=Fischer%2C+K">Kirsten Fischer</a>, <a href="/search/cs?searchtype=author&query=Doerr%2C+A">Andreas Doerr</a>, <a href="/search/cs?searchtype=author&query=Falkner%2C+S">Stefan Falkner</a>, <a href="/search/cs?searchtype=author&query=Hutter%2C+F">Frank Hutter</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christian Daniel</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="1904.02642v5-abstract-short" style="display: inline;"> Transferring knowledge across tasks to improve data-efficiency is one of the open key challenges in the field of global black-box optimization. Readily available algorithms are typically designed to be universal optimizers and, therefore, often suboptimal for specific tasks. We propose a novel transfer learning method to obtain customized optimizers within the well-established framework of Bayesia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.02642v5-abstract-full').style.display = 'inline'; document.getElementById('1904.02642v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.02642v5-abstract-full" style="display: none;"> Transferring knowledge across tasks to improve data-efficiency is one of the open key challenges in the field of global black-box optimization. Readily available algorithms are typically designed to be universal optimizers and, therefore, often suboptimal for specific tasks. We propose a novel transfer learning method to obtain customized optimizers within the well-established framework of Bayesian optimization, allowing our algorithm to utilize the proven generalization capabilities of Gaussian processes. Using reinforcement learning to meta-train an acquisition function (AF) on a set of related tasks, the proposed method learns to extract implicit structural information and to exploit it for improved data-efficiency. We present experiments on a simulation-to-real transfer task as well as on several synthetic functions and on two hyperparameter search problems. The results show that our algorithm (1) automatically identifies structural properties of objective functions from available source tasks or simulations, (2) performs favourably in settings with both scarse and abundant source data, and (3) falls back to the performance level of general AFs if no particular structure is present. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.02642v5-abstract-full').style.display = 'none'; document.getElementById('1904.02642v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1903.07879">arXiv:1903.07879</a> <span> [<a href="https://arxiv.org/pdf/1903.07879">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Hybrid Approaches for our Participation to the n2c2 Challenge on Cohort Selection for Clinical Trials </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tannier%2C+X">Xavier Tannier</a>, <a href="/search/cs?searchtype=author&query=Paris%2C+N">Nicolas Paris</a>, <a href="/search/cs?searchtype=author&query=Cisneros%2C+H">Hugo Cisneros</a>, <a href="/search/cs?searchtype=author&query=Daniel%2C+C">Christel Daniel</a>, <a href="/search/cs?searchtype=author&query=Doutreligne%2C+M">Matthieu Doutreligne</a>, <a href="/search/cs?searchtype=author&query=Duclos%2C+C">Catherine Duclos</a>, <a href="/search/cs?searchtype=author&query=Griffon%2C+N">Nicolas Griffon</a>, <a href="/search/cs?searchtype=author&query=Hassen-Khodja%2C+C">Claire Hassen-Khodja</a>, <a href="/search/cs?searchtype=author&query=Lerner%2C+I">Ivan Lerner</a>, <a href="/search/cs?searchtype=author&query=Parrot%2C+A">Adrien Parrot</a>, <a href="/search/cs?searchtype=author&query=Sadou%2C+%C3%89">脡ric Sadou</a>, <a href="/search/cs?searchtype=author&query=Saussol%2C+C">Cyrina Saussol</a>, <a href="/search/cs?searchtype=author&query=Vaillant%2C+P">Pascal Vaillant</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="1903.07879v2-abstract-short" style="display: inline;"> Objective: Natural language processing can help minimize human intervention in identifying patients meeting eligibility criteria for clinical trials, but there is still a long way to go to obtain a general and systematic approach that is useful for researchers. We describe two methods taking a step in this direction and present their results obtained during the n2c2 challenge on cohort selection f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.07879v2-abstract-full').style.display = 'inline'; document.getElementById('1903.07879v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1903.07879v2-abstract-full" style="display: none;"> Objective: Natural language processing can help minimize human intervention in identifying patients meeting eligibility criteria for clinical trials, but there is still a long way to go to obtain a general and systematic approach that is useful for researchers. We describe two methods taking a step in this direction and present their results obtained during the n2c2 challenge on cohort selection for clinical trials. Materials and Methods: The first method is a weakly supervised method using an unlabeled corpus (MIMIC) to build a silver standard, by producing semi-automatically a small and very precise set of rules to detect some samples of positive and negative patients. This silver standard is then used to train a traditional supervised model. The second method is a terminology-based approach where a medical expert selects the appropriate concepts, and a procedure is defined to search the terms and check the structural or temporal constraints. Results: On the n2c2 dataset containing annotated data about 13 selection criteria on 288 patients, we obtained an overall F1-measure of 0.8969, which is the third best result out of 45 participant teams, with no statistically significant difference with the best-ranked team. Discussion: Both approaches obtained very encouraging results and apply to different types of criteria. The weakly supervised method requires explicit descriptions of positive and negative examples in some reports. The terminology-based method is very efficient when medical concepts carry most of the relevant information. Conclusion: It is unlikely that much more annotated data will be soon available for the task of identifying a wide range of patient phenotypes. One must focus on weakly or non-supervised learning methods using both structured and unstructured data and relying on a comprehensive representation of the patients. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.07879v2-abstract-full').style.display = 'none'; document.getElementById('1903.07879v2-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 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages</span> </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository