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 1–43 of 43 results for author: <span class="mathjax">Gabor, T</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=Gabor%2C+T">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="Gabor, T"> </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=Gabor%2C+T&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="Gabor, T"> <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/2412.07686">arXiv:2412.07686</a> <span> [<a href="https://arxiv.org/pdf/2412.07686">pdf</a>, <a href="https://arxiv.org/format/2412.07686">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="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"> Optimizing Sensor Redundancy in Sequential Decision-Making Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Stein%2C+J">Jonas Stein</a>, <a href="/search/cs?searchtype=author&query=Stenzel%2C+G">Gerhard Stenzel</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6nberger%2C+J">Julian Sch枚nberger</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.07686v1-abstract-short" style="display: inline;"> Reinforcement Learning (RL) policies are designed to predict actions based on current observations to maximize cumulative future rewards. In real-world applications (i.e., non-simulated environments), sensors are essential for measuring the current state and providing the observations on which RL policies rely to make decisions. A significant challenge in deploying RL policies in real-world scenar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07686v1-abstract-full').style.display = 'inline'; document.getElementById('2412.07686v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.07686v1-abstract-full" style="display: none;"> Reinforcement Learning (RL) policies are designed to predict actions based on current observations to maximize cumulative future rewards. In real-world applications (i.e., non-simulated environments), sensors are essential for measuring the current state and providing the observations on which RL policies rely to make decisions. A significant challenge in deploying RL policies in real-world scenarios is handling sensor dropouts, which can result from hardware malfunctions, physical damage, or environmental factors like dust on a camera lens. A common strategy to mitigate this issue is the use of backup sensors, though this comes with added costs. This paper explores the optimization of backup sensor configurations to maximize expected returns while keeping costs below a specified threshold, C. Our approach uses a second-order approximation of expected returns and includes penalties for exceeding cost constraints. We then optimize this quadratic program using Tabu Search, a meta-heuristic algorithm. The approach is evaluated across eight OpenAI Gym environments and a custom Unity-based robotic environment (RobotArmGrasping). Empirical results demonstrate that our quadratic program effectively approximates real expected returns, facilitating the identification of optimal sensor configurations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07686v1-abstract-full').style.display = 'none'; document.getElementById('2412.07686v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ICAART conference 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.04658">arXiv:2411.04658</a> <span> [<a href="https://arxiv.org/pdf/2411.04658">pdf</a>, <a href="https://arxiv.org/format/2411.04658">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"> Finding Strong Lottery Ticket Networks with Genetic Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6nberger%2C+J">Julian Sch枚nberger</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.04658v1-abstract-short" style="display: inline;"> According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the trained super-network. We present the first approach based on a genetic algorithm to find such strong lottery ticket sub-networks without training or otherwise com… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04658v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04658v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04658v1-abstract-full" style="display: none;"> According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the trained super-network. We present the first approach based on a genetic algorithm to find such strong lottery ticket sub-networks without training or otherwise computing any gradient. We show that, for smaller instances of binary classification tasks, our evolutionary approach even produces smaller and better-performing lottery ticket networks than the state-of-the-art approach using gradient information. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04658v1-abstract-full').style.display = 'none'; document.getElementById('2411.04658v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 7 figures, 5 tables, accepted for publication at the 16th International Joint Conference on Computational Intelligence (IJCCI 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/2408.04514">arXiv:2408.04514</a> <span> [<a href="https://arxiv.org/pdf/2408.04514">pdf</a>, <a href="https://arxiv.org/format/2408.04514">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Emergence in Multi-Agent Systems: A Safety Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6nberger%2C+J">Julian Sch枚nberger</a>, <a href="/search/cs?searchtype=author&query=Illium%2C+S">Steffen Illium</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Haider%2C+T">Tom Haider</a>, <a href="/search/cs?searchtype=author&query=Burton%2C+S">Simon Burton</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.04514v1-abstract-short" style="display: inline;"> Emergent effects can arise in multi-agent systems (MAS) where execution is decentralized and reliant on local information. These effects may range from minor deviations in behavior to catastrophic system failures. To formally define these effects, we identify misalignments between the global inherent specification (the true specification) and its local approximation (such as the configuration of d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04514v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04514v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04514v1-abstract-full" style="display: none;"> Emergent effects can arise in multi-agent systems (MAS) where execution is decentralized and reliant on local information. These effects may range from minor deviations in behavior to catastrophic system failures. To formally define these effects, we identify misalignments between the global inherent specification (the true specification) and its local approximation (such as the configuration of different reward components or observations). Using established safety terminology, we develop a framework to understand these emergent effects. To showcase the resulting implications, we use two broadly configurable exemplary gridworld scenarios, where insufficient specification leads to unintended behavior deviations when derived independently. Recognizing that a global adaptation might not always be feasible, we propose adjusting the underlying parameterizations to mitigate these issues, thereby improving the system's alignment and reducing the risk of emergent failures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04514v1-abstract-full').style.display = 'none'; document.getElementById('2408.04514v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 3 figures, accepted for publication at the International Symposium on Leveraging Applications of Formal Methods (ISoLA 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/2408.01187">arXiv:2408.01187</a> <span> [<a href="https://arxiv.org/pdf/2408.01187">pdf</a>, <a href="https://arxiv.org/format/2408.01187">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Optimizing Variational Quantum Circuits Using Metaheuristic Strategies in Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=K%C3%B6lle%2C+M">Michael K枚lle</a>, <a href="/search/cs?searchtype=author&query=Seidl%2C+D">Daniel Seidl</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Stein%2C+J">Jonas Stein</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.01187v1-abstract-short" style="display: inline;"> Quantum Reinforcement Learning (QRL) offers potential advantages over classical Reinforcement Learning, such as compact state space representation and faster convergence in certain scenarios. However, practical benefits require further validation. QRL faces challenges like flat solution landscapes, where traditional gradient-based methods are inefficient, necessitating the use of gradient-free alg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01187v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01187v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01187v1-abstract-full" style="display: none;"> Quantum Reinforcement Learning (QRL) offers potential advantages over classical Reinforcement Learning, such as compact state space representation and faster convergence in certain scenarios. However, practical benefits require further validation. QRL faces challenges like flat solution landscapes, where traditional gradient-based methods are inefficient, necessitating the use of gradient-free algorithms. This work explores the integration of metaheuristic algorithms -- Particle Swarm Optimization, Ant Colony Optimization, Tabu Search, Genetic Algorithm, Simulated Annealing, and Harmony Search -- into QRL. These algorithms provide flexibility and efficiency in parameter optimization. Evaluations in $5\times5$ MiniGrid Reinforcement Learning environments show that, all algorithms yield near-optimal results, with Simulated Annealing and Particle Swarm Optimization performing best. In the Cart Pole environment, Simulated Annealing, Genetic Algorithms, and Particle Swarm Optimization achieve optimal results, while the others perform slightly better than random action selection. These findings demonstrate the potential of Particle Swarm Optimization and Simulated Annealing for efficient QRL learning, emphasizing the need for careful algorithm selection and adaptation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01187v1-abstract-full').style.display = 'none'; document.getElementById('2408.01187v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at QCE24 - QCRL24 Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.12354">arXiv:2405.12354</a> <span> [<a href="https://arxiv.org/pdf/2405.12354">pdf</a>, <a href="https://arxiv.org/format/2405.12354">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> A Study on Optimization Techniques for Variational Quantum Circuits in Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=K%C3%B6lle%2C+M">Michael K枚lle</a>, <a href="/search/cs?searchtype=author&query=Witter%2C+T">Timo Witter</a>, <a href="/search/cs?searchtype=author&query=Rohe%2C+T">Tobias Rohe</a>, <a href="/search/cs?searchtype=author&query=Stenzel%2C+G">Gerhard Stenzel</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</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="2405.12354v1-abstract-short" style="display: inline;"> Quantum Computing aims to streamline machine learning, making it more effective with fewer trainable parameters. This reduction of parameters can speed up the learning process and reduce the use of computational resources. However, in the current phase of quantum computing development, known as the noisy intermediate-scale quantum era (NISQ), learning is difficult due to a limited number of qubits… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.12354v1-abstract-full').style.display = 'inline'; document.getElementById('2405.12354v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.12354v1-abstract-full" style="display: none;"> Quantum Computing aims to streamline machine learning, making it more effective with fewer trainable parameters. This reduction of parameters can speed up the learning process and reduce the use of computational resources. However, in the current phase of quantum computing development, known as the noisy intermediate-scale quantum era (NISQ), learning is difficult due to a limited number of qubits and widespread quantum noise. To overcome these challenges, researchers are focusing on variational quantum circuits (VQCs). VQCs are hybrid algorithms that merge a quantum circuit, which can be adjusted through parameters, with traditional classical optimization techniques. These circuits require only few qubits for effective learning. Recent studies have presented new ways of applying VQCs to reinforcement learning, showing promising results that warrant further exploration. This study investigates the effects of various techniques -- data re-uploading, input scaling, output scaling -- and introduces exponential learning rate decay in the quantum proximal policy optimization algorithm's actor-VQC. We assess these methods in the popular Frozen Lake and Cart Pole environments. Our focus is on their ability to reduce the number of parameters in the VQC without losing effectiveness. Our findings indicate that data re-uploading and an exponential learning rate decay significantly enhance hyperparameter stability and overall performance. While input scaling does not improve parameter efficiency, output scaling effectively manages greediness, leading to increased learning speed and robustness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.12354v1-abstract-full').style.display = 'none'; document.getElementById('2405.12354v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at QSW 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.09272">arXiv:2405.09272</a> <span> [<a href="https://arxiv.org/pdf/2405.09272">pdf</a>, <a href="https://arxiv.org/format/2405.09272">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Using an Evolutionary Algorithm to Create (MAX)-3SAT QUBOs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zielinski%2C+S">Sebastian Zielinski</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="2405.09272v1-abstract-short" style="display: inline;"> A common way of solving satisfiability instances with quantum methods is to transform these instances into instances of QUBO, which in itself is a potentially difficult and expensive task. State-of-the-art transformations from MAX-3SAT to QUBO currently work by mapping clauses of a 3SAT formula associated with the MAX-3SAT instance to an instance of QUBO and combining the resulting QUBOs into a si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09272v1-abstract-full').style.display = 'inline'; document.getElementById('2405.09272v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.09272v1-abstract-full" style="display: none;"> A common way of solving satisfiability instances with quantum methods is to transform these instances into instances of QUBO, which in itself is a potentially difficult and expensive task. State-of-the-art transformations from MAX-3SAT to QUBO currently work by mapping clauses of a 3SAT formula associated with the MAX-3SAT instance to an instance of QUBO and combining the resulting QUBOs into a single QUBO instance representing the whole MAX-3SAT instance. As creating these transformations is currently done manually or via exhaustive search methods and, therefore, algorithmically inefficient, we see potential for including search-based optimization. In this paper, we propose two methods of using evolutionary algorithms to automatically create QUBO representations of MAX-3SAT problems. We evaluate our created QUBOs on 500 and 1000-clause 3SAT formulae and find competitive performance to state-of-the-art baselines when using both classical and quantum annealing solvers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09272v1-abstract-full').style.display = 'none'; document.getElementById('2405.09272v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">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/2404.09213">arXiv:2404.09213</a> <span> [<a href="https://arxiv.org/pdf/2404.09213">pdf</a>, <a href="https://arxiv.org/format/2404.09213">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Qandle: Accelerating State Vector Simulation Using Gate-Matrix Caching and Circuit Splitting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stenzel%2C+G">Gerhard Stenzel</a>, <a href="/search/cs?searchtype=author&query=Zielinski%2C+S">Sebastian Zielinski</a>, <a href="/search/cs?searchtype=author&query=K%C3%B6lle%2C+M">Michael K枚lle</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</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="2404.09213v1-abstract-short" style="display: inline;"> To address the computational complexity associated with state-vector simulation for quantum circuits, we propose a combination of advanced techniques to accelerate circuit execution. Quantum gate matrix caching reduces the overhead of repeated applications of the Kronecker product when applying a gate matrix to the state vector by storing decomposed partial matrices for each gate. Circuit splittin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.09213v1-abstract-full').style.display = 'inline'; document.getElementById('2404.09213v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.09213v1-abstract-full" style="display: none;"> To address the computational complexity associated with state-vector simulation for quantum circuits, we propose a combination of advanced techniques to accelerate circuit execution. Quantum gate matrix caching reduces the overhead of repeated applications of the Kronecker product when applying a gate matrix to the state vector by storing decomposed partial matrices for each gate. Circuit splitting divides the circuit into sub-circuits with fewer gates by constructing a dependency graph, enabling parallel or sequential execution on disjoint subsets of the state vector. These techniques are implemented using the PyTorch machine learning framework. We demonstrate the performance of our approach by comparing it to other PyTorch-compatible quantum state-vector simulators. Our implementation, named Qandle, is designed to seamlessly integrate with existing machine learning workflows, providing a user-friendly API and compatibility with the OpenQASM format. Qandle is an open-source project hosted on GitHub https://github.com/gstenzel/qandle and PyPI https://pypi.org/project/qandle/ . <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.09213v1-abstract-full').style.display = 'none'; document.getElementById('2404.09213v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.03359">arXiv:2404.03359</a> <span> [<a href="https://arxiv.org/pdf/2404.03359">pdf</a>, <a href="https://arxiv.org/format/2404.03359">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Davignon%2C+C">C茅line Davignon</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</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="2404.03359v1-abstract-short" style="display: inline;"> To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-case trajectories provides a more comprehensive understanding of their inherent behavior. To induce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03359v1-abstract-full').style.display = 'inline'; document.getElementById('2404.03359v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.03359v1-abstract-full" style="display: none;"> To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-case trajectories provides a more comprehensive understanding of their inherent behavior. To induce such scenarios, we introduce a disturbance to the initial state, optimizing it through an evolutionary algorithm to generate a diverse population of demonstrations. To evaluate the fitness of trajectories, REACT incorporates a joint fitness function that encourages both local and global diversity in the encountered states and chosen actions. Through assessments with policies trained for varying durations in discrete and continuous environments, we demonstrate the descriptive power of REACT. Our results highlight its effectiveness in revealing nuanced aspects of RL models' behavior beyond optimal performance, thereby contributing to improved interpretability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03359v1-abstract-full').style.display = 'none'; document.getElementById('2404.03359v1-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 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">12 pages, 12 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/2312.11337">arXiv:2312.11337</a> <span> [<a href="https://arxiv.org/pdf/2312.11337">pdf</a>, <a href="https://arxiv.org/format/2312.11337">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Challenges for Reinforcement Learning in Quantum Circuit Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Stein%2C+J">Jonas Stein</a>, <a href="/search/cs?searchtype=author&query=K%C3%B6lle%2C+M">Michael K枚lle</a>, <a href="/search/cs?searchtype=author&query=B%C3%A4rligea%2C+A">Adelina B盲rligea</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="2312.11337v3-abstract-short" style="display: inline;"> Quantum computing (QC) in the current NISQ era is still limited in size and precision. Hybrid applications mitigating those shortcomings are prevalent to gain early insight and advantages. Hybrid quantum machine learning (QML) comprises both the application of QC to improve machine learning (ML) and ML to improve QC architectures. This work considers the latter, leveraging reinforcement learning (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11337v3-abstract-full').style.display = 'inline'; document.getElementById('2312.11337v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.11337v3-abstract-full" style="display: none;"> Quantum computing (QC) in the current NISQ era is still limited in size and precision. Hybrid applications mitigating those shortcomings are prevalent to gain early insight and advantages. Hybrid quantum machine learning (QML) comprises both the application of QC to improve machine learning (ML) and ML to improve QC architectures. This work considers the latter, leveraging reinforcement learning (RL) to improve quantum circuit design (QCD), which we formalize by a set of generic objectives. Furthermore, we propose qcd-gym, a concrete framework formalized as a Markov decision process, to enable learning policies capable of controlling a universal set of continuously parameterized quantum gates. Finally, we provide benchmark comparisons to assess the shortcomings and strengths of current state-of-the-art RL algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11337v3-abstract-full').style.display = 'none'; document.getElementById('2312.11337v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">11 pages, 4 figures, accepted for publication at the 2024 IEEE International Conference on Quantum Computing and Engineering (QCE)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.15966">arXiv:2311.15966</a> <span> [<a href="https://arxiv.org/pdf/2311.15966">pdf</a>, <a href="https://arxiv.org/format/2311.15966">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> <div 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/QCE57702.2023.10182">10.1109/QCE57702.2023.10182 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schuman%2C+D">Dani毛lle Schuman</a>, <a href="/search/cs?searchtype=author&query=S%C3%BCnkel%2C+L">Leo S眉nkel</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Stein%2C+J">Jonas Stein</a>, <a href="/search/cs?searchtype=author&query=Roch%2C+C">Christoph Roch</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="2311.15966v1-abstract-short" style="display: inline;"> Quantum Transfer Learning (QTL) recently gained popularity as a hybrid quantum-classical approach for image classification tasks by efficiently combining the feature extraction capabilities of large Convolutional Neural Networks with the potential benefits of Quantum Machine Learning (QML). Existing approaches, however, only utilize gate-based Variational Quantum Circuits for the quantum part of t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.15966v1-abstract-full').style.display = 'inline'; document.getElementById('2311.15966v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.15966v1-abstract-full" style="display: none;"> Quantum Transfer Learning (QTL) recently gained popularity as a hybrid quantum-classical approach for image classification tasks by efficiently combining the feature extraction capabilities of large Convolutional Neural Networks with the potential benefits of Quantum Machine Learning (QML). Existing approaches, however, only utilize gate-based Variational Quantum Circuits for the quantum part of these procedures. In this work we present an approach to employ Quantum Annealing (QA) in QTL-based image classification. Specifically, we propose using annealing-based Quantum Boltzmann Machines as part of a hybrid quantum-classical pipeline to learn the classification of real-world, large-scale data such as medical images through supervised training. We demonstrate our approach by applying it to the three-class COVID-CT-MD dataset, a collection of lung Computed Tomography (CT) scan slices. Using Simulated Annealing as a stand-in for actual QA, we compare our method to classical transfer learning, using a neural network of the same order of magnitude, to display its improved classification performance. We find that our approach consistently outperforms its classical baseline in terms of test accuracy and AUC-ROC-Score and needs less training epochs to do this. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.15966v1-abstract-full').style.display = 'none'; document.getElementById('2311.15966v1-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 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">7 pages, 3 figures (5 if counting subfigures), 1 table. To be published in the proceedings of the 2023 IEEE International Conference on Quantum Computing and Engineering (QCE)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.19130">arXiv:2305.19130</a> <span> [<a href="https://arxiv.org/pdf/2305.19130">pdf</a>, <a href="https://arxiv.org/ps/2305.19130">ps</a>, <a href="https://arxiv.org/format/2305.19130">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</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/10.21437/Interspeech.2023-1607">10.21437/Interspeech.2023-1607 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=T%C3%B3th%2C+L">L谩szl贸 T贸th</a>, <a href="/search/cs?searchtype=author&query=Shandiz%2C+A+H">Amin Honarmandi Shandiz</a>, <a href="/search/cs?searchtype=author&query=Gosztolya%2C+G">G谩bor Gosztolya</a>, <a href="/search/cs?searchtype=author&query=G%C3%A1bor%2C+C+T">Csap贸 Tam谩s G谩bor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.19130v3-abstract-short" style="display: inline;"> Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather speaker-specific, making a quick switch between users troublesome. Even for the same speaker, these models perform poorly cross-session, i.e. after dismounting and re-mounting… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19130v3-abstract-full').style.display = 'inline'; document.getElementById('2305.19130v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.19130v3-abstract-full" style="display: none;"> Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather speaker-specific, making a quick switch between users troublesome. Even for the same speaker, these models perform poorly cross-session, i.e. after dismounting and re-mounting the recording equipment. To aid quick speaker and session adaptation of ultrasound tongue imaging-based SSI models, we extend our deep networks with a spatial transformer network (STN) module, capable of performing an affine transformation on the input images. Although the STN part takes up only about 10% of the network, our experiments show that adapting just the STN module might allow to reduce MSE by 88% on the average, compared to retraining the whole network. The improvement is even larger (around 92%) when adapting the network to different recording sessions from the same speaker. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19130v3-abstract-full').style.display = 'none'; document.getElementById('2305.19130v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">5 pages, 3 figures, 3 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> the Proceedings of Interspeech 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.03536">arXiv:2302.03536</a> <span> [<a href="https://arxiv.org/pdf/2302.03536">pdf</a>, <a href="https://arxiv.org/format/2302.03536">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Solving (Max) 3-SAT via Quadratic Unconstrained Binary Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=Zielinski%2C+S">Sebastian Zielinski</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</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="2302.03536v1-abstract-short" style="display: inline;"> We introduce a novel approach to translate arbitrary 3-SAT instances to Quadratic Unconstrained Binary Optimization (QUBO) as they are used by quantum annealing (QA) or the quantum approximate optimization algorithm (QAOA). Our approach requires fewer couplings and fewer physical qubits than the current state-of-the-art, which results in higher solution quality. We verified the practical applicabi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03536v1-abstract-full').style.display = 'inline'; document.getElementById('2302.03536v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.03536v1-abstract-full" style="display: none;"> We introduce a novel approach to translate arbitrary 3-SAT instances to Quadratic Unconstrained Binary Optimization (QUBO) as they are used by quantum annealing (QA) or the quantum approximate optimization algorithm (QAOA). Our approach requires fewer couplings and fewer physical qubits than the current state-of-the-art, which results in higher solution quality. We verified the practical applicability of the approach by testing it on a D-Wave quantum annealer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03536v1-abstract-full').style.display = 'none'; document.getElementById('2302.03536v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.07421">arXiv:2301.07421</a> <span> [<a href="https://arxiv.org/pdf/2301.07421">pdf</a>, <a href="https://arxiv.org/format/2301.07421">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"> DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="2301.07421v1-abstract-short" style="display: inline;"> We propose discriminative reward co-training (DIRECT) as an extension to deep reinforcement learning algorithms. Building upon the concept of self-imitation learning (SIL), we introduce an imitation buffer to store beneficial trajectories generated by the policy determined by their return. A discriminator network is trained concurrently to the policy to distinguish between trajectories generated b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.07421v1-abstract-full').style.display = 'inline'; document.getElementById('2301.07421v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.07421v1-abstract-full" style="display: none;"> We propose discriminative reward co-training (DIRECT) as an extension to deep reinforcement learning algorithms. Building upon the concept of self-imitation learning (SIL), we introduce an imitation buffer to store beneficial trajectories generated by the policy determined by their return. A discriminator network is trained concurrently to the policy to distinguish between trajectories generated by the current policy and beneficial trajectories generated by previous policies. The discriminator's verdict is used to construct a reward signal for optimizing the policy. By interpolating prior experience, DIRECT is able to act as a surrogate, steering policy optimization towards more valuable regions of the reward landscape thus learning an optimal policy. Our results show that DIRECT outperforms state-of-the-art algorithms in sparse- and shifting-reward environments being able to provide a surrogate reward to the policy and direct the optimization towards valuable areas. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.07421v1-abstract-full').style.display = 'none'; document.getElementById('2301.07421v1-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 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">9 pages, 10 figures, under review</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.01649">arXiv:2301.01649</a> <span> [<a href="https://arxiv.org/pdf/2301.01649">pdf</a>, <a href="https://arxiv.org/format/2301.01649">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=K%C3%B6lle%2C+M">Michael K枚lle</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="2301.01649v6-abstract-short" style="display: inline;"> Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research due to a strong focus on state-based centralized training for decentralized execution (CTDE) and benchmarks that lack sufficient stochasticity like StarCraft Multi-Agent Challenge (SMAC). In this paper, we propose Attent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.01649v6-abstract-full').style.display = 'inline'; document.getElementById('2301.01649v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.01649v6-abstract-full" style="display: none;"> Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research due to a strong focus on state-based centralized training for decentralized execution (CTDE) and benchmarks that lack sufficient stochasticity like StarCraft Multi-Agent Challenge (SMAC). In this paper, we propose Attention-based Embeddings of Recurrence In multi-Agent Learning (AERIAL) to approximate value functions under stochastic partial observability. AERIAL replaces the true state with a learned representation of multi-agent recurrence, considering more accurate information about decentralized agent decisions than state-based CTDE. We then introduce MessySMAC, a modified version of SMAC with stochastic observations and higher variance in initial states, to provide a more general and configurable benchmark regarding stochastic partial observability. We evaluate AERIAL in Dec-Tiger as well as in a variety of SMAC and MessySMAC maps, and compare the results with state-based CTDE. Furthermore, we evaluate the robustness of AERIAL and state-based CTDE against various stochasticity configurations in MessySMAC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.01649v6-abstract-full').style.display = 'none'; document.getElementById('2301.01649v6-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 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 to ICML 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.11085">arXiv:2212.11085</a> <span> [<a href="https://arxiv.org/pdf/2212.11085">pdf</a>, <a href="https://arxiv.org/format/2212.11085">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="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/10.5220/0010818500003116">10.5220/0010818500003116 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Illium%2C+S">Steffen Illium</a>, <a href="/search/cs?searchtype=author&query=Schillman%2C+T">Thore Schillman</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+R">Robert M眉ller</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.11085v1-abstract-short" style="display: inline;"> Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.11085v1-abstract-full').style.display = 'inline'; document.getElementById('2212.11085v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.11085v1-abstract-full" style="display: none;"> Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backpropagation. However, we also show that for classical RNNs, LSTM and GRU networks the distance of data points between recurrent calls that can be reproduced this way is highly limited (compared to even a loose connection between data points) and subject to various constraints imposed by the type and size of the RNN in question. This implies the existence of a hard limit (way below the information-theoretic one) for the distance between related data points within which RNNs are still able to recognize said relation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.11085v1-abstract-full').style.display = 'none'; document.getElementById('2212.11085v1-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 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.10078">arXiv:2212.10078</a> <span> [<a href="https://arxiv.org/pdf/2212.10078">pdf</a>, <a href="https://arxiv.org/format/2212.10078">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Constructing Organism Networks from Collaborative Self-Replicators </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Illium%2C+S">Steffen Illium</a>, <a href="/search/cs?searchtype=author&query=Zorn%2C+M">Maximilian Zorn</a>, <a href="/search/cs?searchtype=author&query=Lenta%2C+C">Cristian Lenta</a>, <a href="/search/cs?searchtype=author&query=K%C3%B6lle%2C+M">Michael K枚lle</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.10078v2-abstract-short" style="display: inline;"> We introduce organism networks, which function like a single neural network but are composed of several neural particle networks; while each particle network fulfils the role of a single weight application within the organism network, it is also trained to self-replicate its own weights. As organism networks feature vastly more parameters than simpler architectures, we perform our initial experime… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.10078v2-abstract-full').style.display = 'inline'; document.getElementById('2212.10078v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.10078v2-abstract-full" style="display: none;"> We introduce organism networks, which function like a single neural network but are composed of several neural particle networks; while each particle network fulfils the role of a single weight application within the organism network, it is also trained to self-replicate its own weights. As organism networks feature vastly more parameters than simpler architectures, we perform our initial experiments on an arithmetic task as well as on simplified MNIST-dataset classification as a collective. We observe that individual particle networks tend to specialise in either of the tasks and that the ones fully specialised in the secondary task may be dropped from the network without hindering the computational accuracy of the primary task. This leads to the discovery of a novel pruning-strategy for sparse neural networks <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.10078v2-abstract-full').style.display = 'none'; document.getElementById('2212.10078v2-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">2023-02-27 fixed one typo in NN formula</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.05219">arXiv:2208.05219</a> <span> [<a href="https://arxiv.org/pdf/2208.05219">pdf</a>, <a href="https://arxiv.org/format/2208.05219">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-031-19759-8_16">10.1007/978-3-031-19759-8_16 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Capturing Dependencies within Machine Learning via a Formal Process Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Sedlmeier%2C+A">Andreas Sedlmeier</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</a>, <a href="/search/cs?searchtype=author&query=Wieghardt%2C+J">Jan Wieghardt</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+R">Reiner Schmid</a>, <a href="/search/cs?searchtype=author&query=Sauer%2C+H">Horst Sauer</a>, <a href="/search/cs?searchtype=author&query=Klein%2C+C">Cornel Klein</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</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="2208.05219v1-abstract-short" style="display: inline;"> The development of Machine Learning (ML) models is more than just a special case of software development (SD): ML models acquire properties and fulfill requirements even without direct human interaction in a seemingly uncontrollable manner. Nonetheless, the underlying processes can be described in a formal way. We define a comprehensive SD process model for ML that encompasses most tasks and artif… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.05219v1-abstract-full').style.display = 'inline'; document.getElementById('2208.05219v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.05219v1-abstract-full" style="display: none;"> The development of Machine Learning (ML) models is more than just a special case of software development (SD): ML models acquire properties and fulfill requirements even without direct human interaction in a seemingly uncontrollable manner. Nonetheless, the underlying processes can be described in a formal way. We define a comprehensive SD process model for ML that encompasses most tasks and artifacts described in the literature in a consistent way. In addition to the production of the necessary artifacts, we also focus on generating and validating fitting descriptions in the form of specifications. We stress the importance of further evolving the ML model throughout its life-cycle even after initial training and testing. Thus, we provide various interaction points with standard SD processes in which ML often is an encapsulated task. Further, our SD process model allows to formulate ML as a (meta-) optimization problem. If automated rigorously, it can be used to realize self-adaptive autonomous systems. Finally, our SD process model features a description of time that allows to reason about the progress within ML development processes. This might lead to further applications of formal methods within the field of ML. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.05219v1-abstract-full').style.display = 'none'; document.getElementById('2208.05219v1-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">10 pages, 5 figures, draft; the final version will appear in the proceedings of the International Symposium on Leveraging Applications of Formal Methods (ISoLA) 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ISoLA 2022: Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning. pp 249-265 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.12510">arXiv:2206.12510</a> <span> [<a href="https://arxiv.org/pdf/2206.12510">pdf</a>, <a href="https://arxiv.org/format/2206.12510">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"> Black Box Optimization Using QUBO and the Cross Entropy Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=Roch%2C+C">Christoph Roch</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Stein%2C+J">Jonas Stein</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.12510v3-abstract-short" style="display: inline;"> Black-box optimization (BBO) can be used to optimize functions whose analytic form is unknown. A common approach to realising BBO is to learn a surrogate model which approximates the target black-box function which can then be solved via white-box optimization methods. In this paper, we present our approach BOX-QUBO, where the surrogate model is a QUBO matrix. However, unlike in previous state-of-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.12510v3-abstract-full').style.display = 'inline'; document.getElementById('2206.12510v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.12510v3-abstract-full" style="display: none;"> Black-box optimization (BBO) can be used to optimize functions whose analytic form is unknown. A common approach to realising BBO is to learn a surrogate model which approximates the target black-box function which can then be solved via white-box optimization methods. In this paper, we present our approach BOX-QUBO, where the surrogate model is a QUBO matrix. However, unlike in previous state-of-the-art approaches, this matrix is not trained entirely by regression, but mostly by classification between 'good' and 'bad' solutions. This better accounts for the low capacity of the QUBO matrix, resulting in significantly better solutions overall. We tested our approach against the state-of-the-art on four domains and in all of them BOX-QUBO showed better results. A second contribution of this paper is the idea to also solve white-box problems, i.e. problems which could be directly formulated as QUBO, by means of black-box optimization in order to reduce the size of the QUBOs to the information-theoretic minimum. Experiments show that this significantly improves the results for MAX-k-SAT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.12510v3-abstract-full').style.display = 'none'; document.getElementById('2206.12510v3-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.05827">arXiv:2206.05827</a> <span> [<a href="https://arxiv.org/pdf/2206.05827">pdf</a>, <a href="https://arxiv.org/format/2206.05827">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"> Case-Based Inverse Reinforcement Learning Using Temporal Coherence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=Illium%2C+S">Steffen Illium</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+R">Robert M眉ller</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.05827v1-abstract-short" style="display: inline;"> Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm that imitates the higher-level strategy of the expert rather than just imitating the expert on action level, which we hypothesize requires less expert data and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.05827v1-abstract-full').style.display = 'inline'; document.getElementById('2206.05827v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.05827v1-abstract-full" style="display: none;"> Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm that imitates the higher-level strategy of the expert rather than just imitating the expert on action level, which we hypothesize requires less expert data and makes training more stable. As a prior, we assume that the higher-level strategy is to reach an unknown target state area, which we hypothesize is a valid prior for many domains in Reinforcement Learning. The target state area is unknown, but since the expert has demonstrated how to reach it, the agent tries to reach states similar to the expert. Building on the idea of Temporal Coherence, our algorithm trains a neural network to predict whether two states are similar, in the sense that they may occur close in time. During inference, the agent compares its current state with expert states from a Case Base for similarity. The results show that our approach can still learn a near-optimal policy in settings with very little expert data, where algorithms that try to imitate the expert at the action level can no longer do so. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.05827v1-abstract-full').style.display = 'none'; document.getElementById('2206.05827v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted at ICCBR</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.13539">arXiv:2204.13539</a> <span> [<a href="https://arxiv.org/pdf/2204.13539">pdf</a>, <a href="https://arxiv.org/format/2204.13539">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</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/10.1145/3520304.3533952">10.1145/3520304.3533952 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Algorithmic QUBO Formulations for k-SAT and Hamiltonian Cycles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=N%C3%BC%C3%9Flein%2C+J">Jonas N眉脽lein</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</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="2204.13539v1-abstract-short" style="display: inline;"> Quadratic unconstrained binary optimization (QUBO) can be seen as a generic language for optimization problems. QUBOs attract particular attention since they can be solved with quantum hardware, like quantum annealers or quantum gate computers running QAOA. In this paper, we present two novel QUBO formulations for $k$-SAT and Hamiltonian Cycles that scale significantly better than existing approac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.13539v1-abstract-full').style.display = 'inline'; document.getElementById('2204.13539v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.13539v1-abstract-full" style="display: none;"> Quadratic unconstrained binary optimization (QUBO) can be seen as a generic language for optimization problems. QUBOs attract particular attention since they can be solved with quantum hardware, like quantum annealers or quantum gate computers running QAOA. In this paper, we present two novel QUBO formulations for $k$-SAT and Hamiltonian Cycles that scale significantly better than existing approaches. For $k$-SAT we reduce the growth of the QUBO matrix from $O(k)$ to $O(log(k))$. For Hamiltonian Cycles the matrix no longer grows quadratically in the number of nodes, as currently, but linearly in the number of edges and logarithmically in the number of nodes. We present these two formulations not as mathematical expressions, as most QUBO formulations are, but as meta-algorithms that facilitate the design of more complex QUBO formulations and allow easy reuse in larger and more complex QUBO formulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.13539v1-abstract-full').style.display = 'none'; document.getElementById('2204.13539v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at GECCO 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/2109.10617">arXiv:2109.10617</a> <span> [<a href="https://arxiv.org/pdf/2109.10617">pdf</a>, <a href="https://arxiv.org/format/2109.10617">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Solving Large Steiner Tree Problems in Graphs for Cost-Efficient Fiber-To-The-Home Network Expansion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+T">Tobias M眉ller</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+K">Kyrill Schmid</a>, <a href="/search/cs?searchtype=author&query=Schuman%2C+D">Dani毛lle Schuman</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Friedrich%2C+M">Markus Friedrich</a>, <a href="/search/cs?searchtype=author&query=Geitz%2C+M">Marc Geitz</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="2109.10617v2-abstract-short" style="display: inline;"> The expansion of Fiber-To-The-Home (FTTH) networks creates high costs due to expensive excavation procedures. Optimizing the planning process and minimizing the cost of the earth excavation work therefore lead to large savings. Mathematically, the FTTH network problem can be described as a minimum Steiner Tree problem. Even though the Steiner Tree problem has already been investigated intensively… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.10617v2-abstract-full').style.display = 'inline'; document.getElementById('2109.10617v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.10617v2-abstract-full" style="display: none;"> The expansion of Fiber-To-The-Home (FTTH) networks creates high costs due to expensive excavation procedures. Optimizing the planning process and minimizing the cost of the earth excavation work therefore lead to large savings. Mathematically, the FTTH network problem can be described as a minimum Steiner Tree problem. Even though the Steiner Tree problem has already been investigated intensively in the last decades, it might be further optimized with the help of new computing paradigms and emerging approaches. This work studies upcoming technologies, such as Quantum Annealing, Simulated Annealing and nature-inspired methods like Evolutionary Algorithms or slime-mold-based optimization. Additionally, we investigate partitioning and simplifying methods. Evaluated on several real-life problem instances, we could outperform a traditional, widely-used baseline (NetworkX Approximate Solver) on most of the domains. Prior partitioning of the initial graph and the presented slime-mold-based approach were especially valuable for a cost-efficient approximation. Quantum Annealing seems promising, but was limited by the number of available qubits. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.10617v2-abstract-full').style.display = 'none'; document.getElementById('2109.10617v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ICAART 2022, 10 pages, 18 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.07949">arXiv:2012.07949</a> <span> [<a href="https://arxiv.org/pdf/2012.07949">pdf</a>, <a href="https://arxiv.org/format/2012.07949">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="Multiagent Systems">cs.MA</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/10.5220/0010189500280037">10.5220/0010189500280037 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+R">Robert M眉ller</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Sedlmeier%2C+A">Andreas Sedlmeier</a>, <a href="/search/cs?searchtype=author&query=Zeller%2C+M">Marc Zeller</a>, <a href="/search/cs?searchtype=author&query=Wieghardt%2C+J">Jan Wieghardt</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+R">Reiner Schmid</a>, <a href="/search/cs?searchtype=author&query=Sauer%2C+H">Horst Sauer</a>, <a href="/search/cs?searchtype=author&query=Klein%2C+C">Cornel Klein</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2012.07949v1-abstract-short" style="display: inline;"> A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In industrial scenarios, a system's behavior also needs to be predictable and lie within defined ranges. To enable the agents to learn (how) to align with a given s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.07949v1-abstract-full').style.display = 'inline'; document.getElementById('2012.07949v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.07949v1-abstract-full" style="display: none;"> A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In industrial scenarios, a system's behavior also needs to be predictable and lie within defined ranges. To enable the agents to learn (how) to align with a given specification, this paper proposes to explicitly transfer functional and non-functional requirements into shaped rewards. Experiments are carried out on the smart factory, a multi-agent environment modeling an industrial lot-size-one production facility, with up to eight agents and different multi-agent reinforcement learning algorithms. Results indicate that compliance with functional and non-functional constraints can be achieved by the proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.07949v1-abstract-full').style.display = 'none'; document.getElementById('2012.07949v1-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 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">9 pages, 5 figures; accepted as a full paper at ICAART 2021 (http://www.icaart.org/)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, 28-37, 2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.14036">arXiv:2004.14036</a> <span> [<a href="https://arxiv.org/pdf/2004.14036">pdf</a>, <a href="https://arxiv.org/format/2004.14036">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Insights on Training Neural Networks for QUBO Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=Safi%2C+H">Hila Safi</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2004.14036v1-abstract-short" style="display: inline;"> Current hardware limitations restrict the potential when solving quadratic unconstrained binary optimization (QUBO) problems via the quantum approximate optimization algorithm (QAOA) or quantum annealing (QA). Thus, we consider training neural networks in this context. We first discuss QUBO problems that originate from translated instances of the traveling salesman problem (TSP): Analyzing this re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.14036v1-abstract-full').style.display = 'inline'; document.getElementById('2004.14036v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.14036v1-abstract-full" style="display: none;"> Current hardware limitations restrict the potential when solving quadratic unconstrained binary optimization (QUBO) problems via the quantum approximate optimization algorithm (QAOA) or quantum annealing (QA). Thus, we consider training neural networks in this context. We first discuss QUBO problems that originate from translated instances of the traveling salesman problem (TSP): Analyzing this representation via autoencoders shows that there is way more information included than necessary to solve the original TSP. Then we show that neural networks can be used to solve TSP instances from both QUBO input and autoencoders' hiddenstate representation. We finally generalize the approach and successfully train neural networks to solve arbitrary QUBO problems, sketching means to use neuromorphic hardware as a simulator or an additional co-processor for quantum computing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.14036v1-abstract-full').style.display = 'none'; document.getElementById('2004.14036v1-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 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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, 5 figures, accepted at the 1st International Workshop on Quantum Software Engineering (Q-SE 2020) at ICSE 2020 and to be published in the corresponding proceedings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.14035">arXiv:2004.14035</a> <span> [<a href="https://arxiv.org/pdf/2004.14035">pdf</a>, <a href="https://arxiv.org/format/2004.14035">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> The Holy Grail of Quantum Artificial Intelligence: Major Challenges in Accelerating the Machine Learning Pipeline </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=S%C3%BCnkel%2C+L">Leo S眉nkel</a>, <a href="/search/cs?searchtype=author&query=Ritz%2C+F">Fabian Ritz</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Roch%2C+C">Christoph Roch</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2004.14035v1-abstract-short" style="display: inline;"> We discuss the synergetic connection between quantum computing and artificial intelligence. After surveying current approaches to quantum artificial intelligence and relating them to a formal model for machine learning processes, we deduce four major challenges for the future of quantum artificial intelligence: (i) Replace iterative training with faster quantum algorithms, (ii) distill the experie… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.14035v1-abstract-full').style.display = 'inline'; document.getElementById('2004.14035v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.14035v1-abstract-full" style="display: none;"> We discuss the synergetic connection between quantum computing and artificial intelligence. After surveying current approaches to quantum artificial intelligence and relating them to a formal model for machine learning processes, we deduce four major challenges for the future of quantum artificial intelligence: (i) Replace iterative training with faster quantum algorithms, (ii) distill the experience of larger amounts of data into the training process, (iii) allow quantum and classical components to be easily combined and exchanged, and (iv) build tools to thoroughly analyze whether observed benefits really stem from quantum properties of the algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.14035v1-abstract-full').style.display = 'none'; document.getElementById('2004.14035v1-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 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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, 4 figures, accepted at the 1st International Workshop on Quantum Software Engineering (Q-SE 2020) at ICSE 2020 and to be published in the corresponding proceedings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2001.00496">arXiv:2001.00496</a> <span> [<a href="https://arxiv.org/pdf/2001.00496">pdf</a>, <a href="https://arxiv.org/format/2001.00496">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 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/10.5220/0008949905220529">10.5220/0008949905220529 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sedlmeier%2C+A">Andreas Sedlmeier</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="2001.00496v1-abstract-short" style="display: inline;"> Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class cl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.00496v1-abstract-full').style.display = 'inline'; document.getElementById('2001.00496v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2001.00496v1-abstract-full" style="display: none;"> Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class classification problem, we propose a framework for uncertainty-based OOD classification: UBOOD. It is based on the effect that an agent's epistemic uncertainty is reduced for situations encountered during training (in-distribution), and thus lower than for unencountered (OOD) situations. Being agnostic towards the approach used for estimating epistemic uncertainty, combinations with different uncertainty estimation methods, e.g. approximate Bayesian inference methods or ensembling techniques are possible. We further present a first viable solution for calculating a dynamic classification threshold, based on the uncertainty distribution of the training data. Evaluation shows that the framework produces reliable classification results when combined with ensemble-based estimators, while the combination with concrete dropout-based estimators fails to reliably detect OOD situations. In summary, UBOOD presents a viable approach for OOD classification in deep RL settings by leveraging the epistemic uncertainty of the agent's value function. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.00496v1-abstract-full').style.display = 'none'; document.getElementById('2001.00496v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">arXiv admin note: text overlap with arXiv:1901.02219</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, 2020, ISBN 978-989-758-395-7, pages 522-529 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.06032">arXiv:1912.06032</a> <span> [<a href="https://arxiv.org/pdf/1912.06032">pdf</a>, <a href="https://arxiv.org/format/1912.06032">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Integration and Evaluation of Quantum Accelerators for Data-Driven User Functions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hubregtsen%2C+T">Thomas Hubregtsen</a>, <a href="/search/cs?searchtype=author&query=Segler%2C+C">Christoph Segler</a>, <a href="/search/cs?searchtype=author&query=Pichlmeier%2C+J">Josef Pichlmeier</a>, <a href="/search/cs?searchtype=author&query=Sarkar%2C+A">Aritra Sarkar</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Bertels%2C+K">Koen Bertels</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.06032v2-abstract-short" style="display: inline;"> Quantum computers hold great promise for accelerating computationally challenging algorithms on noisy intermediate-scale quantum (NISQ) devices in the upcoming years. Much attention of the current research is directed to algorithmic research on artificial data that is disconnected from live systems, such as optimization of systems or training of learning algorithms. In this paper we investigate th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.06032v2-abstract-full').style.display = 'inline'; document.getElementById('1912.06032v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.06032v2-abstract-full" style="display: none;"> Quantum computers hold great promise for accelerating computationally challenging algorithms on noisy intermediate-scale quantum (NISQ) devices in the upcoming years. Much attention of the current research is directed to algorithmic research on artificial data that is disconnected from live systems, such as optimization of systems or training of learning algorithms. In this paper we investigate the integration of quantum systems into industry-grade system architectures. In this work we propose a system architecture for the integration of quantum accelerators. In order to evaluate our proposed system architecture we implemented various algorithms including a classical system, a gate-based quantum accelerator and a quantum annealer. This algorithm automates user habits using data-driven functions trained on real-world data. This also includes an evaluation of the quantum enhanced kernel, that previously was only evaluated on artificial data. In our evaluation, we showed that the quantum-enhanced kernel performs at least equally well to a classical state-of-the-art kernel. We also showed a low reduction in accuracy and latency numbers within acceptable bounds when running on the gate-based IBM quantum accelerator. We, therefore, conclude it is feasible to integrate NISQ-era devices in industry-grade system architecture in preparation for future hardware improvements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.06032v2-abstract-full').style.display = 'none'; document.getElementById('1912.06032v2-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, accepted to ISQED 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/1908.02880">arXiv:1908.02880</a> <span> [<a href="https://arxiv.org/pdf/1908.02880">pdf</a>, <a href="https://arxiv.org/format/1908.02880">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"> Benchmarking Surrogate-Assisted Genetic Recommender Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+P">Philipp Altmann</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="1908.02880v1-abstract-short" style="display: inline;"> We propose a new approach for building recommender systems by adapting surrogate-assisted interactive genetic algorithms. A pool of user-evaluated items is used to construct an approximative model which serves as a surrogate fitness function in a genetic algorithm for optimizing new suggestions. The surrogate is used to recommend new items to the user, which are then evaluated according to the use… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.02880v1-abstract-full').style.display = 'inline'; document.getElementById('1908.02880v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1908.02880v1-abstract-full" style="display: none;"> We propose a new approach for building recommender systems by adapting surrogate-assisted interactive genetic algorithms. A pool of user-evaluated items is used to construct an approximative model which serves as a surrogate fitness function in a genetic algorithm for optimizing new suggestions. The surrogate is used to recommend new items to the user, which are then evaluated according to the user's liking and subsequently removed from the search space. By updating the surrogate model after new recommendations have been evaluated by the user, we enable the model itself to evolve towards the user's preferences. In order to precisely evaluate the performance of that approach, the human's subjective evaluation is replaced by common continuous objective benchmark functions for evolutionary algorithms. The system's performance is compared to a conventional genetic algorithm and random search. We show that given a very limited amount of allowed evaluations on the true objective, our approach outperforms these baseline methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.02880v1-abstract-full').style.display = 'none'; document.getElementById('1908.02880v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">Proceedings of the Genetic and Evolutionary Computation Conference Companion. ACM, 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/1907.05861">arXiv:1907.05861</a> <span> [<a href="https://arxiv.org/pdf/1907.05861">pdf</a>, <a href="https://arxiv.org/format/1907.05861">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> </div> </div> <p class="title is-5 mathjax"> Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+R">Robert M眉ller</a>, <a href="/search/cs?searchtype=author&query=Roch%2C+C">Christoph Roch</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="1907.05861v2-abstract-short" style="display: inline;"> We propose Stable Yet Memory Bounded Open-Loop (SYMBOL) planning, a general memory bounded approach to partially observable open-loop planning. SYMBOL maintains an adaptive stack of Thompson Sampling bandits, whose size is bounded by the planning horizon and can be automatically adapted according to the underlying domain without any prior domain knowledge beyond a generative model. We empirically… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.05861v2-abstract-full').style.display = 'inline'; document.getElementById('1907.05861v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.05861v2-abstract-full" style="display: none;"> We propose Stable Yet Memory Bounded Open-Loop (SYMBOL) planning, a general memory bounded approach to partially observable open-loop planning. SYMBOL maintains an adaptive stack of Thompson Sampling bandits, whose size is bounded by the planning horizon and can be automatically adapted according to the underlying domain without any prior domain knowledge beyond a generative model. We empirically test SYMBOL in four large POMDP benchmark problems to demonstrate its effectiveness and robustness w.r.t. the choice of hyperparameters and evaluate its adaptive memory consumption. We also compare its performance with other open-loop planning algorithms and POMCP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.05861v2-abstract-full').style.display = 'none'; document.getElementById('1907.05861v2-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">Accepted to IJCAI 2019. arXiv admin note: substantial text overlap with arXiv:1905.04020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.04077">arXiv:1905.04077</a> <span> [<a href="https://arxiv.org/pdf/1905.04077">pdf</a>, <a href="https://arxiv.org/format/1905.04077">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Emergent Escape-based Flocking Behavior using Multi-Agent Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hahn%2C+C">Carsten Hahn</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="1905.04077v1-abstract-short" style="display: inline;"> In nature, flocking or swarm behavior is observed in many species as it has beneficial properties like reducing the probability of being caught by a predator. In this paper, we propose SELFish (Swarm Emergent Learning Fish), an approach with multiple autonomous agents which can freely move in a continuous space with the objective to avoid being caught by a present predator. The predator has the pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.04077v1-abstract-full').style.display = 'inline'; document.getElementById('1905.04077v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.04077v1-abstract-full" style="display: none;"> In nature, flocking or swarm behavior is observed in many species as it has beneficial properties like reducing the probability of being caught by a predator. In this paper, we propose SELFish (Swarm Emergent Learning Fish), an approach with multiple autonomous agents which can freely move in a continuous space with the objective to avoid being caught by a present predator. The predator has the property that it might get distracted by multiple possible preys in its vicinity. We show that this property in interaction with self-interested agents which are trained with reinforcement learning to solely survive as long as possible leads to flocking behavior similar to Boids, a common simulation for flocking behavior. Furthermore we present interesting insights in the swarming behavior and in the process of agents being caught in our modeled environment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.04077v1-abstract-full').style.display = 'none'; document.getElementById('1905.04077v1-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 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">Accepted at ALIFE 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/1903.06454">arXiv:1903.06454</a> <span> [<a href="https://arxiv.org/pdf/1903.06454">pdf</a>, <a href="https://arxiv.org/format/1903.06454">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> A Quantum Annealing Algorithm for Finding Pure Nash Equilibria in Graphical Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roch%2C+C">Christoph Roch</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+R">Robert M眉ller</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="1903.06454v2-abstract-short" style="display: inline;"> We introduce Q-Nash, a quantum annealing algorithm for the NP-complete problem of Fnding pure Nash equilibria in graphical games. The algorithm consists of two phases. The first phase determines all combinations of best response strategies for each player using classical computation. The second phase finds pure Nash equilibria using a quantum annealing device by mapping the computed combinations t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.06454v2-abstract-full').style.display = 'inline'; document.getElementById('1903.06454v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1903.06454v2-abstract-full" style="display: none;"> We introduce Q-Nash, a quantum annealing algorithm for the NP-complete problem of Fnding pure Nash equilibria in graphical games. The algorithm consists of two phases. The first phase determines all combinations of best response strategies for each player using classical computation. The second phase finds pure Nash equilibria using a quantum annealing device by mapping the computed combinations to a quadratic unconstrained binary optimization formulation based on the Set Cover problem. We empirically evaluate Q-Nash on D-Wave's Quantum Annealer 2000Q using different graphical game topologies. The results with respect to solution quality and computing time are compared to a Brute Force algorithm and the Iterated Best Response heuristic. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.06454v2-abstract-full').style.display = 'none'; document.getElementById('1903.06454v2-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1902.04703">arXiv:1902.04703</a> <span> [<a href="https://arxiv.org/pdf/1902.04703">pdf</a>, <a href="https://arxiv.org/format/1902.04703">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Complexity">cs.CC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> </div> </div> <p class="title is-5 mathjax"> Assessing Solution Quality of 3SAT on a Quantum Annealing Platform </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Zielinski%2C+S">Sebastian Zielinski</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=Roch%2C+C">Christoph Roch</a>, <a href="/search/cs?searchtype=author&query=Seidel%2C+C">Christian Seidel</a>, <a href="/search/cs?searchtype=author&query=Neukart%2C+F">Florian Neukart</a>, <a href="/search/cs?searchtype=author&query=Galter%2C+I">Isabella Galter</a>, <a href="/search/cs?searchtype=author&query=Mauerer%2C+W">Wolfgang Mauerer</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="1902.04703v1-abstract-short" style="display: inline;"> When solving propositional logic satisfiability (specifically 3SAT) using quantum annealing, we analyze the effect the difficulty of different instances of the problem has on the quality of the answer returned by the quantum annealer. A high-quality response from the annealer in this case is defined by a high percentage of correct solutions among the returned answers. We show that the phase transi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.04703v1-abstract-full').style.display = 'inline'; document.getElementById('1902.04703v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.04703v1-abstract-full" style="display: none;"> When solving propositional logic satisfiability (specifically 3SAT) using quantum annealing, we analyze the effect the difficulty of different instances of the problem has on the quality of the answer returned by the quantum annealer. A high-quality response from the annealer in this case is defined by a high percentage of correct solutions among the returned answers. We show that the phase transition regarding the computational complexity of the problem, which is well-known to occur for 3SAT on classical machines (where it causes a detrimental increase in runtime), persists in some form (but possibly to a lesser extent) for quantum annealing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.04703v1-abstract-full').style.display = 'none'; document.getElementById('1902.04703v1-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 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">13 pages, published at QTOP 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/1902.04694">arXiv:1902.04694</a> <span> [<a href="https://arxiv.org/pdf/1902.04694">pdf</a>, <a href="https://arxiv.org/ps/1902.04694">ps</a>, <a href="https://arxiv.org/format/1902.04694">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-030-03424-5_10">10.1007/978-3-030-03424-5_10 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Adapting Quality Assurance to Adaptive Systems: The Scenario Coevolution Paradigm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Kiermeier%2C+M">Marie Kiermeier</a>, <a href="/search/cs?searchtype=author&query=Sedlmeier%2C+A">Andreas Sedlmeier</a>, <a href="/search/cs?searchtype=author&query=Kempter%2C+B">Bernhard Kempter</a>, <a href="/search/cs?searchtype=author&query=Klein%2C+C">Cornel Klein</a>, <a href="/search/cs?searchtype=author&query=Sauer%2C+H">Horst Sauer</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+R">Reiner Schmid</a>, <a href="/search/cs?searchtype=author&query=Wieghardt%2C+J">Jan Wieghardt</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="1902.04694v1-abstract-short" style="display: inline;"> From formal and practical analysis, we identify new challenges that self-adaptive systems pose to the process of quality assurance. When tackling these, the effort spent on various tasks in the process of software engineering is naturally re-distributed. We claim that all steps related to testing need to become self-adaptive to match the capabilities of the self-adaptive system-under-test. Otherwi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.04694v1-abstract-full').style.display = 'inline'; document.getElementById('1902.04694v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.04694v1-abstract-full" style="display: none;"> From formal and practical analysis, we identify new challenges that self-adaptive systems pose to the process of quality assurance. When tackling these, the effort spent on various tasks in the process of software engineering is naturally re-distributed. We claim that all steps related to testing need to become self-adaptive to match the capabilities of the self-adaptive system-under-test. Otherwise, the adaptive system's behavior might elude traditional variants of quality assurance. We thus propose the paradigm of scenario coevolution, which describes a pool of test cases and other constraints on system behavior that evolves in parallel to the (in part autonomous) development of behavior in the system-under-test. Scenario coevolution offers a simple structure for the organization of adaptive testing that allows for both human-controlled and autonomous intervention, supporting software engineering for adaptive systems on a procedural as well as technical level. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.04694v1-abstract-full').style.display = 'none'; document.getElementById('1902.04694v1-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 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">17 pages, published at ISOLA 2018</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> International Symposium on Leveraging Applications of Formal Methods (ISOLA). Springer, 2018 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.08761">arXiv:1901.08761</a> <span> [<a href="https://arxiv.org/pdf/1901.08761">pdf</a>, <a href="https://arxiv.org/format/1901.08761">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="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+K">Kyrill Schmid</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Feld%2C+S">Sebastian Feld</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1901.08761v1-abstract-short" style="display: inline;"> Decision making in multi-agent systems (MAS) is a great challenge due to enormous state and joint action spaces as well as uncertainty, making centralized control generally infeasible. Decentralized control offers better scalability and robustness but requires mechanisms to coordinate on joint tasks and to avoid conflicts. Common approaches to learn decentralized policies for cooperative MAS suffe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.08761v1-abstract-full').style.display = 'inline'; document.getElementById('1901.08761v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.08761v1-abstract-full" style="display: none;"> Decision making in multi-agent systems (MAS) is a great challenge due to enormous state and joint action spaces as well as uncertainty, making centralized control generally infeasible. Decentralized control offers better scalability and robustness but requires mechanisms to coordinate on joint tasks and to avoid conflicts. Common approaches to learn decentralized policies for cooperative MAS suffer from non-stationarity and lacking credit assignment, which can lead to unstable and uncoordinated behavior in complex environments. In this paper, we propose Strong Emergent Policy approximation (STEP), a scalable approach to learn strong decentralized policies for cooperative MAS with a distributed variant of policy iteration. For that, we use function approximation to learn from action recommendations of a decentralized multi-agent planning algorithm. STEP combines decentralized multi-agent planning with centralized learning, only requiring a generative model for distributed black box optimization. We experimentally evaluate STEP in two challenging and stochastic domains with large state and joint action spaces and show that STEP is able to learn stronger policies than standard multi-agent reinforcement learning algorithms, when combining multi-agent open-loop planning with centralized function approximation. The learned policies can be reintegrated into the multi-agent planning process to further improve performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.08761v1-abstract-full').style.display = 'none'; document.getElementById('1901.08761v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.02219">arXiv:1901.02219</a> <span> [<a href="https://arxiv.org/pdf/1901.02219">pdf</a>, <a href="https://arxiv.org/format/1901.02219">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"> Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sedlmeier%2C+A">Andreas Sedlmeier</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1901.02219v1-abstract-short" style="display: inline;"> We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value estimating neural network to detect OOD samples. The focus of our work lies in analyzing the suitability of approximate Bayesian inference methods and related ensembl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.02219v1-abstract-full').style.display = 'inline'; document.getElementById('1901.02219v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.02219v1-abstract-full" style="display: none;"> We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value estimating neural network to detect OOD samples. The focus of our work lies in analyzing the suitability of approximate Bayesian inference methods and related ensembling techniques that generate uncertainty estimates. Although prior work has shown that dropout-based variational inference techniques and bootstrap-based approaches can be used to model epistemic uncertainty, the suitability for detecting OOD samples in deep reinforcement learning remains an open question. Our results show that uncertainty estimation can be used to differentiate in- from out-of-distribution samples. Over the complete training process of the reinforcement learning agents, bootstrap-based approaches tend to produce more reliable epistemic uncertainty estimates, when compared to dropout-based approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.02219v1-abstract-full').style.display = 'none'; document.getElementById('1901.02219v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.12483">arXiv:1810.12483</a> <span> [<a href="https://arxiv.org/pdf/1810.12483">pdf</a>, <a href="https://arxiv.org/format/1810.12483">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/10.1109/ICAC.2018.00023">10.1109/ICAC.2018.00023 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Preparing for the Unexpected: Diversity Improves Planning Resilience in Evolutionary Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+K">Kyrill Schmid</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="1810.12483v1-abstract-short" style="display: inline;"> As automatic optimization techniques find their way into industrial applications, the behavior of many complex systems is determined by some form of planner picking the right actions to optimize a given objective function. In many cases, the mapping of plans to objective reward may change due to unforeseen events or circumstances in the real world. In those cases, the planner usually needs some ad… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.12483v1-abstract-full').style.display = 'inline'; document.getElementById('1810.12483v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.12483v1-abstract-full" style="display: none;"> As automatic optimization techniques find their way into industrial applications, the behavior of many complex systems is determined by some form of planner picking the right actions to optimize a given objective function. In many cases, the mapping of plans to objective reward may change due to unforeseen events or circumstances in the real world. In those cases, the planner usually needs some additional effort to adjust to the changed situation and reach its previous level of performance. Whenever we still need to continue polling the planner even during re-planning, it oftentimes exhibits severely lacking performance. In order to improve the planner's resilience to unforeseen change, we argue that maintaining a certain level of diversity amongst the considered plans at all times should be added to the planner's objective. Effectively, we encourage the planner to keep alternative plans to its currently best solution. As an example case, we implement a diversity-aware genetic algorithm using two different metrics for diversity (differing in their generality) and show that the blow in performance due to unexpected change can be severely lessened in the average case. We also analyze the parameter settings necessary for these techniques in order to gain an intuition how they can be incorporated into larger frameworks or process models for software and systems engineering. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.12483v1-abstract-full').style.display = 'none'; document.getElementById('1810.12483v1-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 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICAC, 2018, Trento</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.12470">arXiv:1810.12470</a> <span> [<a href="https://arxiv.org/pdf/1810.12470">pdf</a>, <a href="https://arxiv.org/format/1810.12470">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/10.1145/3205455.3205630">10.1145/3205455.3205630 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Inheritance-Based Diversity Measures for Explicit Convergence Control in Evolutionary Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Linnhoff-Popien%2C+C">Claudia Linnhoff-Popien</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="1810.12470v1-abstract-short" style="display: inline;"> Diversity is an important factor in evolutionary algorithms to prevent premature convergence towards a single local optimum. In order to maintain diversity throughout the process of evolution, various means exist in literature. We analyze approaches to diversity that (a) have an explicit and quantifiable influence on fitness at the individual level and (b) require no (or very little) additional do… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.12470v1-abstract-full').style.display = 'inline'; document.getElementById('1810.12470v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.12470v1-abstract-full" style="display: none;"> Diversity is an important factor in evolutionary algorithms to prevent premature convergence towards a single local optimum. In order to maintain diversity throughout the process of evolution, various means exist in literature. We analyze approaches to diversity that (a) have an explicit and quantifiable influence on fitness at the individual level and (b) require no (or very little) additional domain knowledge such as domain-specific distance functions. We also introduce the concept of genealogical diversity in a broader study. We show that employing these approaches can help evolutionary algorithms for global optimization in many cases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.12470v1-abstract-full').style.display = 'none'; document.getElementById('1810.12470v1-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 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">GECCO '18: Genetic and Evolutionary Computation Conference, 2018, Kyoto, Japan</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.10781">arXiv:1804.10781</a> <span> [<a href="https://arxiv.org/pdf/1804.10781">pdf</a>, <a href="https://arxiv.org/format/1804.10781">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> The Sharer's Dilemma in Collective Adaptive Systems of Self-Interested Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+K">Kyrill Schmid</a>, <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Wirsing%2C+M">Martin Wirsing</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="1804.10781v1-abstract-short" style="display: inline;"> In collective adaptive systems (CAS), adaptation can be implemented by optimization wrt. utility. Agents in a CAS may be self-interested, while their utilities may depend on other agents' choices. Independent optimization of agent utilities may yield poor individual and global reward due to locally interfering individual preferences. Joint optimization may scale poorly, and is impossible if agents… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.10781v1-abstract-full').style.display = 'inline'; document.getElementById('1804.10781v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.10781v1-abstract-full" style="display: none;"> In collective adaptive systems (CAS), adaptation can be implemented by optimization wrt. utility. Agents in a CAS may be self-interested, while their utilities may depend on other agents' choices. Independent optimization of agent utilities may yield poor individual and global reward due to locally interfering individual preferences. Joint optimization may scale poorly, and is impossible if agents cannot expose their preferences due to privacy or security issues. In this paper, we study utility sharing for mitigating this issue. Sharing utility with others may incentivize individuals to consider choices that are locally suboptimal but increase global reward. We illustrate our approach with a utility sharing variant of distributed cross entropy optimization. Empirical results show that utility sharing increases expected individual and global payoff in comparison to optimization without utility sharing. We also investigate the effect of greedy defectors in a CAS of sharing, self-interested agents. We observe that defection increases the mean expected individual payoff at the expense of sharing individuals' payoff. We empirically show that the choice between defection and sharing yields a fundamental dilemma for self-interested agents in a CAS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.10781v1-abstract-full').style.display = 'none'; document.getElementById('1804.10781v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.06311">arXiv:1804.06311</a> <span> [<a href="https://arxiv.org/pdf/1804.06311">pdf</a>, <a href="https://arxiv.org/format/1804.06311">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+T">Thomy Phan</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Schmid%2C+K">Kyrill Schmid</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="1804.06311v2-abstract-short" style="display: inline;"> Making decisions is a great challenge in distributed autonomous environments due to enormous state spaces and uncertainty. Many online planning algorithms rely on statistical sampling to avoid searching the whole state space, while still being able to make acceptable decisions. However, planning often has to be performed under strict computational constraints making online planning in multi-agent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.06311v2-abstract-full').style.display = 'inline'; document.getElementById('1804.06311v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.06311v2-abstract-full" style="display: none;"> Making decisions is a great challenge in distributed autonomous environments due to enormous state spaces and uncertainty. Many online planning algorithms rely on statistical sampling to avoid searching the whole state space, while still being able to make acceptable decisions. However, planning often has to be performed under strict computational constraints making online planning in multi-agent systems highly limited, which could lead to poor system performance, especially in stochastic domains. In this paper, we propose Emergent Value function Approximation for Distributed Environments (EVADE), an approach to integrate global experience into multi-agent online planning in stochastic domains to consider global effects during local planning. For this purpose, a value function is approximated online based on the emergent system behaviour by using methods of reinforcement learning. We empirically evaluated EVADE with two statistical multi-agent online planning algorithms in a highly complex and stochastic smart factory environment, where multiple agents need to process various items at a shared set of machines. Our experiments show that EVADE can effectively improve the performance of multi-agent online planning while offering efficiency w.r.t. the breadth and depth of the planning process. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.06311v2-abstract-full').style.display = 'none'; document.getElementById('1804.06311v2-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to AAMAS 2018</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1704.08774">arXiv:1704.08774</a> <span> [<a href="https://arxiv.org/pdf/1704.08774">pdf</a>, <a href="https://arxiv.org/format/1704.08774">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/10.1145/3067695.3082529">10.1145/3067695.3082529 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Genealogical Distance as a Diversity Estimate in Evolutionary Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a>, <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</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="1704.08774v1-abstract-short" style="display: inline;"> The evolutionary edit distance between two individuals in a population, i.e., the amount of applications of any genetic operator it would take the evolutionary process to generate one individual starting from the other, seems like a promising estimate for the diversity between said individuals. We introduce genealogical diversity, i.e., estimating two individuals' degree of relatedness by analyzin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1704.08774v1-abstract-full').style.display = 'inline'; document.getElementById('1704.08774v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1704.08774v1-abstract-full" style="display: none;"> The evolutionary edit distance between two individuals in a population, i.e., the amount of applications of any genetic operator it would take the evolutionary process to generate one individual starting from the other, seems like a promising estimate for the diversity between said individuals. We introduce genealogical diversity, i.e., estimating two individuals' degree of relatedness by analyzing large, unused parts of their genome, as a computationally efficient method to approximate that measure for diversity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1704.08774v1-abstract-full').style.display = 'none'; document.getElementById('1704.08774v1-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 April, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Measuring and Promoting Diversity in Evolutionary Algorithms @ GECCO 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1703.10669">arXiv:1703.10669</a> <span> [<a href="https://arxiv.org/pdf/1703.10669">pdf</a>, <a href="https://arxiv.org/format/1703.10669">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="Software Engineering">cs.SE</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/FAS-W.2016.36">10.1109/FAS-W.2016.36 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> QoS-Aware Multi-Armed Bandits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</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="1703.10669v1-abstract-short" style="display: inline;"> Motivated by runtime verification of QoS requirements in self-adaptive and self-organizing systems that are able to reconfigure their structure and behavior in response to runtime data, we propose a QoS-aware variant of Thompson sampling for multi-armed bandits. It is applicable in settings where QoS satisfaction of an arm has to be ensured with high confidence efficiently, rather than finding the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1703.10669v1-abstract-full').style.display = 'inline'; document.getElementById('1703.10669v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1703.10669v1-abstract-full" style="display: none;"> Motivated by runtime verification of QoS requirements in self-adaptive and self-organizing systems that are able to reconfigure their structure and behavior in response to runtime data, we propose a QoS-aware variant of Thompson sampling for multi-armed bandits. It is applicable in settings where QoS satisfaction of an arm has to be ensured with high confidence efficiently, rather than finding the optimal arm while minimizing regret. Preliminary experimental results encourage further research in the field of QoS-aware decision making. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1703.10669v1-abstract-full').style.display = 'none'; document.getElementById('1703.10669v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at IEEE Workshop on Quality Assurance for Self-adaptive Self-organising Systems, FAS* 2016</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1702.08726">arXiv:1702.08726</a> <span> [<a href="https://arxiv.org/pdf/1702.08726">pdf</a>, <a href="https://arxiv.org/format/1702.08726">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Stacked Thompson Bandits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1702.08726v1-abstract-short" style="display: inline;"> We introduce Stacked Thompson Bandits (STB) for efficiently generating plans that are likely to satisfy a given bounded temporal logic requirement. STB uses a simulation for evaluation of plans, and takes a Bayesian approach to using the resulting information to guide its search. In particular, we show that stacking multiarmed bandits and using Thompson sampling to guide the action selection proce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.08726v1-abstract-full').style.display = 'inline'; document.getElementById('1702.08726v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1702.08726v1-abstract-full" style="display: none;"> We introduce Stacked Thompson Bandits (STB) for efficiently generating plans that are likely to satisfy a given bounded temporal logic requirement. STB uses a simulation for evaluation of plans, and takes a Bayesian approach to using the resulting information to guide its search. In particular, we show that stacking multiarmed bandits and using Thompson sampling to guide the action selection process for each bandit enables STB to generate plans that satisfy requirements with a high probability while only searching a fraction of the search space. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.08726v1-abstract-full').style.display = 'none'; document.getElementById('1702.08726v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at SEsCPS @ ICSE 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1702.08725">arXiv:1702.08725</a> <span> [<a href="https://arxiv.org/pdf/1702.08725">pdf</a>, <a href="https://arxiv.org/format/1702.08725">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Bayesian Verification under Model Uncertainty </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1702.08725v1-abstract-short" style="display: inline;"> Machine learning enables systems to build and update domain models based on runtime observations. In this paper, we study statistical model checking and runtime verification for systems with this ability. Two challenges arise: (1) Models built from limited runtime data yield uncertainty to be dealt with. (2) There is no definition of satisfaction w.r.t. uncertain hypotheses. We propose such a defi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.08725v1-abstract-full').style.display = 'inline'; document.getElementById('1702.08725v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1702.08725v1-abstract-full" style="display: none;"> Machine learning enables systems to build and update domain models based on runtime observations. In this paper, we study statistical model checking and runtime verification for systems with this ability. Two challenges arise: (1) Models built from limited runtime data yield uncertainty to be dealt with. (2) There is no definition of satisfaction w.r.t. uncertain hypotheses. We propose such a definition of subjective satisfaction based on recently introduced satisfaction functions. We also propose the BV algorithm as a Bayesian solution to runtime verification of subjective satisfaction under model uncertainty. BV provides user-definable stochastic bounds for type I and II errors. We discuss empirical results from an example application to illustrate our ideas. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.08725v1-abstract-full').style.display = 'none'; document.getElementById('1702.08725v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at SEsCPS @ ICSE 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1702.07544">arXiv:1702.07544</a> <span> [<a href="https://arxiv.org/pdf/1702.07544">pdf</a>, <a href="https://arxiv.org/format/1702.07544">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Scalable Multiagent Coordination with Distributed Online Open Loop Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Belzner%2C+L">Lenz Belzner</a>, <a href="/search/cs?searchtype=author&query=Gabor%2C+T">Thomas Gabor</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1702.07544v1-abstract-short" style="display: inline;"> We propose distributed online open loop planning (DOOLP), a general framework for online multiagent coordination and decision making under uncertainty. DOOLP is based on online heuristic search in the space defined by a generative model of the domain dynamics, which is exploited by agents to simulate and evaluate the consequences of their potential choices. We also propose distributed online Tho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.07544v1-abstract-full').style.display = 'inline'; document.getElementById('1702.07544v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1702.07544v1-abstract-full" style="display: none;"> We propose distributed online open loop planning (DOOLP), a general framework for online multiagent coordination and decision making under uncertainty. DOOLP is based on online heuristic search in the space defined by a generative model of the domain dynamics, which is exploited by agents to simulate and evaluate the consequences of their potential choices. We also propose distributed online Thompson sampling (DOTS) as an effective instantiation of the DOOLP framework. DOTS models sequences of agent choices by concatenating a number of multiarmed bandits for each agent and uses Thompson sampling for dealing with action value uncertainty. The Bayesian approach underlying Thompson sampling allows to effectively model and estimate uncertainty about (a) own action values and (b) other agents' behavior. This approach yields a principled and statistically sound solution to the exploration-exploitation dilemma when exploring large search spaces with limited resources. We implemented DOTS in a smart factory case study with positive empirical results. We observed effective, robust and scalable planning and coordination capabilities even when only searching a fraction of the potential search space. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1702.07544v1-abstract-full').style.display = 'none'; document.getElementById('1702.07544v1-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 February, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2017. </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