Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 175 results for author: <span class="mathjax">Di, S</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Di%2C+S">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Di, S"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Di%2C+S&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Di, S"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Di%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.16851">arXiv:2502.16851</a> <span> [<a href="https://arxiv.org/pdf/2502.16851">pdf</a>, <a href="https://arxiv.org/format/2502.16851">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Can Tensor Cores Benefit Memory-Bound Kernels? (No!) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Lingqi Zhang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Matsuoka%2C+S">Satoshi Matsuoka</a>, <a href="/search/cs?searchtype=author&query=Wahib%2C+M">Mohamed Wahib</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="2502.16851v1-abstract-short" style="display: inline;"> Tensor cores are specialized processing units within GPUs that have demonstrated significant efficiency gains in compute-bound applications such as Deep Learning Training by accelerating dense matrix operations. Given their success, researchers have attempted to extend tensor core capabilities beyond dense matrix computations to other computational patterns, including memory-bound kernels. Recent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.16851v1-abstract-full').style.display = 'inline'; document.getElementById('2502.16851v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.16851v1-abstract-full" style="display: none;"> Tensor cores are specialized processing units within GPUs that have demonstrated significant efficiency gains in compute-bound applications such as Deep Learning Training by accelerating dense matrix operations. Given their success, researchers have attempted to extend tensor core capabilities beyond dense matrix computations to other computational patterns, including memory-bound kernels. Recent studies have reported that tensor cores can outperform traditional CUDA cores even on memory-bound kernels, where the primary performance bottleneck is not computation. In this research, we challenge these findings through both theoretical and empirical analysis. Our theoretical analysis reveals that tensor cores can achieve a maximum speedup of only 1.33x over CUDA cores for memory-bound kernels in double precision (for V100, A100, and H100 GPUs). We validate this theoretical limit through empirical analysis of three representative memory-bound kernels-STREAM Scale, SpMV, and stencil. We demonstrate that optimizing memory-bound kernels using tensor cores does not yield sound performance improvements over CUDA cores. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.16851v1-abstract-full').style.display = 'none'; document.getElementById('2502.16851v1-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, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.04093">arXiv:2502.04093</a> <span> [<a href="https://arxiv.org/pdf/2502.04093">pdf</a>, <a href="https://arxiv.org/format/2502.04093">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> PSZ: Enhancing the SZ Scientific Lossy Compressor With Progressive Data Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhuoxun Yang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Longtao Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruoyu Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Ximiao Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kai Zhao</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="2502.04093v2-abstract-short" style="display: inline;"> Compression is a crucial solution for data reduction in modern scientific applications due to the exponential growth of data from simulations, experiments, and observations. Compression with progressive retrieval capability allows users to access coarse approximations of data quickly and then incrementally refine these approximations to higher fidelity. Existing progressive compression solutions s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04093v2-abstract-full').style.display = 'inline'; document.getElementById('2502.04093v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.04093v2-abstract-full" style="display: none;"> Compression is a crucial solution for data reduction in modern scientific applications due to the exponential growth of data from simulations, experiments, and observations. Compression with progressive retrieval capability allows users to access coarse approximations of data quickly and then incrementally refine these approximations to higher fidelity. Existing progressive compression solutions suffer from low reduction ratios or high operation costs, effectively undermining the approach's benefits. In this paper, we propose the first-ever interpolation-based progressive lossy compression solution that has both high reduction ratios and low operation costs. The interpolation-based algorithm has been verified as one of the best for scientific data reduction, but previously no effort exists to make it support progressive retrieval. Our contributions are three-fold: (1) We thoroughly analyze the error characteristics of the interpolation algorithm and propose our solution IPComp with multi-level bitplane and predictive coding. (2) We derive optimized strategies toward minimum data retrieval under different fidelity levels indicated by users through error bounds and bitrates. (3) We evaluate the proposed solution using six real-world datasets from four diverse domains. Experimental results demonstrate our solution archives up to $487\%$ higher compression ratios and $698\%$ faster speed than other state-of-the-art progressive compressors, and reduces the data volume for retrieval by up to $83\%$ compared to baselines under the same error bound, and reduces the error by up to $99\%$ under the same bitrate. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04093v2-abstract-full').style.display = 'none'; document.getElementById('2502.04093v2-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, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.08222">arXiv:2501.08222</a> <span> [<a href="https://arxiv.org/pdf/2501.08222">pdf</a>, <a href="https://arxiv.org/format/2501.08222">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Data-driven Spatial Classification using Multi-Arm Bandits for Monitoring with Energy-Constrained Mobile Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lin%2C+X">Xiaoshan Lin</a>, <a href="/search/cs?searchtype=author&query=Nayak%2C+S">Siddharth Nayak</a>, <a href="/search/cs?searchtype=author&query=Di+Cairano%2C+S">Stefano Di Cairano</a>, <a href="/search/cs?searchtype=author&query=Vinod%2C+A+P">Abraham P. Vinod</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.08222v1-abstract-short" style="display: inline;"> We consider the spatial classification problem for monitoring using data collected by a coordinated team of mobile robots. Such classification problems arise in several applications including search-and-rescue and precision agriculture. Specifically, we want to classify the regions of a search environment into interesting and uninteresting as quickly as possible using a team of mobile sensors and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08222v1-abstract-full').style.display = 'inline'; document.getElementById('2501.08222v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.08222v1-abstract-full" style="display: none;"> We consider the spatial classification problem for monitoring using data collected by a coordinated team of mobile robots. Such classification problems arise in several applications including search-and-rescue and precision agriculture. Specifically, we want to classify the regions of a search environment into interesting and uninteresting as quickly as possible using a team of mobile sensors and mobile charging stations. We develop a data-driven strategy that accommodates the noise in sensed data and the limited energy capacity of the sensors, and generates collision-free motion plans for the team. We propose a bi-level approach, where a high-level planner leverages a multi-armed bandit framework to determine the potential regions of interest for the drones to visit next based on the data collected online. Then, a low-level path planner based on integer programming coordinates the paths for the team to visit the target regions subject to the physical constraints. We characterize several theoretical properties of the proposed approach, including anytime guarantees and task completion time. We show the efficacy of our approach in simulation, and further validate these observations in physical experiments using mobile robots. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.08222v1-abstract-full').style.display = 'none'; document.getElementById('2501.08222v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 6 figures. See https://www.youtube.com/watch?v=gzulpOcVYzg for an overview of the approach along with videos of the hardware experiments</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.05821">arXiv:2501.05821</a> <span> [<a href="https://arxiv.org/pdf/2501.05821">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> Analysing the coverage of the University of Bologna's publication metadata in an existing source of open research information </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Andreose%2C+E">Erica Andreose</a>, <a href="/search/cs?searchtype=author&query=Di+Marzo%2C+S">Salvatore Di Marzo</a>, <a href="/search/cs?searchtype=author&query=Heibi%2C+I">Ivan Heibi</a>, <a href="/search/cs?searchtype=author&query=Peroni%2C+S">Silvio Peroni</a>, <a href="/search/cs?searchtype=author&query=Zilli%2C+L">Leonardo Zilli</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.05821v1-abstract-short" style="display: inline;"> This study focuses on analysing the coverage of publications' metadata available in the Current Research Information System (CRIS) infrastructure of the University of Bologna (UNIBO), implemented by the IRIS platform, within an authoritative source of open research information, i.e. OpenCitations. The analysis considers data regarding the publication entities alongside the citation links. We preci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05821v1-abstract-full').style.display = 'inline'; document.getElementById('2501.05821v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.05821v1-abstract-full" style="display: none;"> This study focuses on analysing the coverage of publications' metadata available in the Current Research Information System (CRIS) infrastructure of the University of Bologna (UNIBO), implemented by the IRIS platform, within an authoritative source of open research information, i.e. OpenCitations. The analysis considers data regarding the publication entities alongside the citation links. We precisely quantify the proportion of UNIBO IRIS publications included in OpenCitations, examine their types, and evaluate the number of citations in OpenCitations that involve IRIS publications. Our methodology filters and transforms data dumps of IRIS and OpenCitations, creating novel datasets used for the analysis. Our findings reveal that only 37.7% of IRIS is covered in OpenCitations, with journal articles exhibiting the highest coverage. We identified 4,290,096 citation links pointing to UNIBO IRIS publications. From a purely quantitative perspective, comparing our results with broader proprietary services like Scopus and Web of Science reveals a small gap in the average number of citations per bibliographic resource. However, further analysis with updated data is required to support this speculation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05821v1-abstract-full').style.display = 'none'; document.getElementById('2501.05821v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.13049">arXiv:2412.13049</a> <span> [<a href="https://arxiv.org/pdf/2412.13049">pdf</a>, <a href="https://arxiv.org/format/2412.13049">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <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"> TIMESAFE: Timing Interruption Monitoring and Security Assessment for Fronthaul Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Groen%2C+J">Joshua Groen</a>, <a href="/search/cs?searchtype=author&query=Di+Valerio%2C+S">Simone Di Valerio</a>, <a href="/search/cs?searchtype=author&query=Karim%2C+I">Imtiaz Karim</a>, <a href="/search/cs?searchtype=author&query=Villa%2C+D">Davide Villa</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yiewi Zhang</a>, <a href="/search/cs?searchtype=author&query=Bonati%2C+L">Leonardo Bonati</a>, <a href="/search/cs?searchtype=author&query=Polese%2C+M">Michele Polese</a>, <a href="/search/cs?searchtype=author&query=D%27Oro%2C+S">Salvatore D'Oro</a>, <a href="/search/cs?searchtype=author&query=Melodia%2C+T">Tommaso Melodia</a>, <a href="/search/cs?searchtype=author&query=Bertino%2C+E">Elisa Bertino</a>, <a href="/search/cs?searchtype=author&query=Cuomo%2C+F">Francesca Cuomo</a>, <a href="/search/cs?searchtype=author&query=Chowdhury%2C+K">Kaushik Chowdhury</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="2412.13049v1-abstract-short" style="display: inline;"> 5G and beyond cellular systems embrace the disaggregation of Radio Access Network (RAN) components, exemplified by the evolution of the fronthual (FH) connection between cellular baseband and radio unit equipment. Crucially, synchronization over the FH is pivotal for reliable 5G services. In recent years, there has been a push to move these links to an Ethernet-based packet network topology, lever… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13049v1-abstract-full').style.display = 'inline'; document.getElementById('2412.13049v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.13049v1-abstract-full" style="display: none;"> 5G and beyond cellular systems embrace the disaggregation of Radio Access Network (RAN) components, exemplified by the evolution of the fronthual (FH) connection between cellular baseband and radio unit equipment. Crucially, synchronization over the FH is pivotal for reliable 5G services. In recent years, there has been a push to move these links to an Ethernet-based packet network topology, leveraging existing standards and ongoing research for Time-Sensitive Networking (TSN). However, TSN standards, such as Precision Time Protocol (PTP), focus on performance with little to no concern for security. This increases the exposure of the open FH to security risks. Attacks targeting synchronization mechanisms pose significant threats, potentially disrupting 5G networks and impairing connectivity. In this paper, we demonstrate the impact of successful spoofing and replay attacks against PTP synchronization. We show how a spoofing attack is able to cause a production-ready O-RAN and 5G-compliant private cellular base station to catastrophically fail within 2 seconds of the attack, necessitating manual intervention to restore full network operations. To counter this, we design a Machine Learning (ML)-based monitoring solution capable of detecting various malicious attacks with over 97.5% accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13049v1-abstract-full').style.display = 'none'; document.getElementById('2412.13049v1-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 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">ACM Class:</span> C.2; C.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.05824">arXiv:2412.05824</a> <span> [<a href="https://arxiv.org/pdf/2412.05824">pdf</a>, <a href="https://arxiv.org/format/2412.05824">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> TurboFFT: Co-Designed High-Performance and Fault-Tolerant Fast Fourier Transform on GPUs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shixun Wu</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+Y">Yujia Zhai</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Jian%2C+Z">Zizhe Jian</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+H">Huangliang Dai</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zizhong Chen</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="2412.05824v1-abstract-short" style="display: inline;"> GPU-based fast Fourier transform (FFT) is extremely important for scientific computing and signal processing. However, we find the inefficiency of existing FFT libraries and the absence of fault tolerance against soft error. To address these issues, we introduce TurboFFT, a new FFT prototype co-designed for high performance and online fault tolerance. For FFT, we propose an architecture-aware, pad… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05824v1-abstract-full').style.display = 'inline'; document.getElementById('2412.05824v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.05824v1-abstract-full" style="display: none;"> GPU-based fast Fourier transform (FFT) is extremely important for scientific computing and signal processing. However, we find the inefficiency of existing FFT libraries and the absence of fault tolerance against soft error. To address these issues, we introduce TurboFFT, a new FFT prototype co-designed for high performance and online fault tolerance. For FFT, we propose an architecture-aware, padding-free, and template-based prototype to maximize hardware resource utilization, achieving a competitive or superior performance compared to the state-of-the-art closed-source library, cuFFT. For fault tolerance, we 1) explore algorithm-based fault tolerance (ABFT) at the thread and threadblock levels to reduce additional memory footprint, 2) address the error propagation by introducing a two-side ABFT with location encoding, and 3) further modify the threadblock-level FFT from 1-transaction to multi-transaction in order to bring more parallelism for ABFT. Our two-side strategy enables online correction without additional global memory while our multi-transaction design averages the expensive threadblock-level reduction in ABFT with zero additional operations. Experimental results on an NVIDIA A100 server GPU and a Tesla Turing T4 GPU demonstrate that TurboFFT without fault tolerance is comparable to or up to 300\% faster than cuFFT and outperforms VkFFT. TurboFFT with fault tolerance maintains an overhead of 7\% to 15\%, even under tens of error injections per minute for both FP32 and FP64. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.05824v1-abstract-full').style.display = 'none'; document.getElementById('2412.05824v1-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 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">arXiv admin note: substantial text overlap with arXiv:2405.02520</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.02799">arXiv:2412.02799</a> <span> [<a href="https://arxiv.org/pdf/2412.02799">pdf</a>, <a href="https://arxiv.org/format/2412.02799">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> QPET: A Versatile and Portable Quantity-of-Interest-preservation Framework for Error-Bounded Lossy Compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Jiao%2C+P">Pu Jiao</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kai Zhao</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xin Liang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</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="2412.02799v1-abstract-short" style="display: inline;"> Error-bounded lossy compression has been widely adopted in many scientific domains because it can address the challenges in storing, transferring, and analyzing the unprecedented amount of scientific data. Although error-bounded lossy compression offers general data distortion control by enforcing strict error bounds on raw data, they may fail to meet the quality requirements on the results of dow… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.02799v1-abstract-full').style.display = 'inline'; document.getElementById('2412.02799v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.02799v1-abstract-full" style="display: none;"> Error-bounded lossy compression has been widely adopted in many scientific domains because it can address the challenges in storing, transferring, and analyzing the unprecedented amount of scientific data. Although error-bounded lossy compression offers general data distortion control by enforcing strict error bounds on raw data, they may fail to meet the quality requirements on the results of downstream analysis derived from raw data, a.k.a Quantities of Interest (QoIs). This may lead to uncertainties and even misinterpretations in scientific discoveries, significantly limiting the use of lossy compression in practice. In this paper, we propose QPET, a novel, versatile, and portable framework for QoI-preserving error-bounded lossy compression, which overcomes the challenges of modeling diverse QoIs by leveraging numerical strategies. QPET features (1) high portability to multiple existing lossy compressors, (2) versatile preservation to most differentiable univariate and multivariate QoIs, and (3) significant compression improvements in QoI-preservation tasks. Experiments with six real-world datasets demonstrate that QPET outperformed existing QoI-preserving compression framework in terms of speed, and integrating QPET into state-of-the-art error-bounded lossy compressors can gain up to 250% compression ratio improvements to original compressors and up to 75% compression ratio improvements to existing QoI-integrated scientific compressors. Under the same level of peak signal-to-noise ratios in the QoIs, QPET can improve the compression ratio by up to 102%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.02799v1-abstract-full').style.display = 'none'; document.getElementById('2412.02799v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.01694">arXiv:2412.01694</a> <span> [<a href="https://arxiv.org/pdf/2412.01694">pdf</a>, <a href="https://arxiv.org/format/2412.01694">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+Y">Yudi Shi</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Shangzhe Di</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qirui Chen</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+W">Weidi Xie</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="2412.01694v2-abstract-short" style="display: inline;"> This paper tackles the problem of video question answering (VideoQA), a task that often requires multi-step reasoning and a profound understanding of spatial-temporal dynamics. While large video-language models perform well on benchmarks, they often lack explainability and spatial-temporal grounding. In this paper, we propose Agent-of-Thoughts Distillation (AoTD), a method that enhances models by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01694v2-abstract-full').style.display = 'inline'; document.getElementById('2412.01694v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01694v2-abstract-full" style="display: none;"> This paper tackles the problem of video question answering (VideoQA), a task that often requires multi-step reasoning and a profound understanding of spatial-temporal dynamics. While large video-language models perform well on benchmarks, they often lack explainability and spatial-temporal grounding. In this paper, we propose Agent-of-Thoughts Distillation (AoTD), a method that enhances models by incorporating automatically generated Chain-of-Thoughts (CoTs) into the instruction-tuning process. Specifically, we leverage an agent-based system to decompose complex questions into sub-tasks, and address them with specialized vision models, the intermediate results are then treated as reasoning chains. We also introduce a verification mechanism using a large language model (LLM) to ensure the reliability of generated CoTs. Extensive experiments demonstrate that AoTD improves the performance on multiple-choice and open-ended benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01694v2-abstract-full').style.display = 'none'; document.getElementById('2412.01694v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.09471">arXiv:2411.09471</a> <span> [<a href="https://arxiv.org/pdf/2411.09471">pdf</a>, <a href="https://arxiv.org/format/2411.09471">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Renal Cell Carcinoma subtyping: learning from multi-resolution localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mohamad%2C+M">Mohamad Mohamad</a>, <a href="/search/cs?searchtype=author&query=Ponzio%2C+F">Francesco Ponzio</a>, <a href="/search/cs?searchtype=author&query=Di+Cataldo%2C+S">Santa Di Cataldo</a>, <a href="/search/cs?searchtype=author&query=Ambrosetti%2C+D">Damien Ambrosetti</a>, <a href="/search/cs?searchtype=author&query=Descombes%2C+X">Xavier Descombes</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="2411.09471v1-abstract-short" style="display: inline;"> Renal Cell Carcinoma is typically asymptomatic at the early stages for many patients. This leads to a late diagnosis of the tumor, where the curability likelihood is lower, and makes the mortality rate of Renal Cell Carcinoma high, with respect to its incidence rate. To increase the survival chance, a fast and correct categorization of the tumor subtype is paramount. Nowadays, computerized methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09471v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09471v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09471v1-abstract-full" style="display: none;"> Renal Cell Carcinoma is typically asymptomatic at the early stages for many patients. This leads to a late diagnosis of the tumor, where the curability likelihood is lower, and makes the mortality rate of Renal Cell Carcinoma high, with respect to its incidence rate. To increase the survival chance, a fast and correct categorization of the tumor subtype is paramount. Nowadays, computerized methods, based on artificial intelligence, represent an interesting opportunity to improve the productivity and the objectivity of the microscopy-based Renal Cell Carcinoma diagnosis. Nonetheless, much of their exploitation is hampered by the paucity of annotated dataset, essential for a proficient training of supervised machine learning technologies. This study sets out to investigate a novel self supervised training strategy for machine learning diagnostic tools, based on the multi-resolution nature of the histological samples. We aim at reducing the need of annotated dataset, without significantly reducing the accuracy of the tool. We demonstrate the classification capability of our tool on a whole slide imaging dataset for Renal Cancer subtyping, and we compare our solution with several state-of-the-art classification counterparts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09471v1-abstract-full').style.display = 'none'; document.getElementById('2411.09471v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00761">arXiv:2411.00761</a> <span> [<a href="https://arxiv.org/pdf/2411.00761">pdf</a>, <a href="https://arxiv.org/format/2411.00761">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> LCP: Enhancing Scientific Data Management with Lossy Compression for Particles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Longtao Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+R">Ruoyu Li</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+C">Congrong Ren</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Underwood%2C+R">Robert Underwood</a>, <a href="/search/cs?searchtype=author&query=Grosset%2C+P">Pascal Grosset</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+D">Dingwen Tao</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xin Liang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hanqi Guo</a>, <a href="/search/cs?searchtype=author&query=Capello%2C+F">Franck Capello</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kai Zhao</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="2411.00761v1-abstract-short" style="display: inline;"> Many scientific applications opt for particles instead of meshes as their basic primitives to model complex systems composed of billions of discrete entities. Such applications span a diverse array of scientific domains, including molecular dynamics, cosmology, computational fluid dynamics, and geology. The scale of the particles in those scientific applications increases substantially thanks to t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00761v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00761v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00761v1-abstract-full" style="display: none;"> Many scientific applications opt for particles instead of meshes as their basic primitives to model complex systems composed of billions of discrete entities. Such applications span a diverse array of scientific domains, including molecular dynamics, cosmology, computational fluid dynamics, and geology. The scale of the particles in those scientific applications increases substantially thanks to the ever-increasing computational power in high-performance computing (HPC) platforms. However, the actual gains from such increases are often undercut by obstacles in data management systems related to data storage, transfer, and processing. Lossy compression has been widely recognized as a promising solution to enhance scientific data management systems regarding such challenges, although most existing compression solutions are tailored for Cartesian grids and thus have sub-optimal results on discrete particle data. In this paper, we introduce LCP, an innovative lossy compressor designed for particle datasets, offering superior compression quality and higher speed than existing compression solutions. Specifically, our contribution is threefold. (1) We propose LCP-S, an error-bound aware block-wise spatial compressor to efficiently reduce particle data size. This approach is universally applicable to particle data across various domains. (2) We develop LCP, a hybrid compression solution for multi-frame particle data, featuring dynamic method selection and parameter optimization. (3) We evaluate our solution alongside eight state-of-the-art alternatives on eight real-world particle datasets from seven distinct domains. The results demonstrate that our solution achieves up to 104% improvement in compression ratios and up to 593% increase in speed compared to the second-best option, under the same error criteria. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00761v1-abstract-full').style.display = 'none'; document.getElementById('2411.00761v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 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">Accepted by SIGMOD'25</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.23497">arXiv:2410.23497</a> <span> [<a href="https://arxiv.org/pdf/2410.23497">pdf</a>, <a href="https://arxiv.org/format/2410.23497">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> To Compress or Not To Compress: Energy Trade-Offs and Benefits of Lossy Compressed I/O </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wilkins%2C+G">Grant Wilkins</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Calhoun%2C+J+C">Jon C. Calhoun</a>, <a href="/search/cs?searchtype=author&query=Underwood%2C+R">Robert Underwood</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.23497v1-abstract-short" style="display: inline;"> Modern scientific simulations generate massive volumes of data, creating significant challenges for I/O and storage systems. Error-bounded lossy compression (EBLC) offers a solution by reducing dataset sizes while preserving data quality within user-specified limits. This study provides the first comprehensive energy characterization of state-of-the-art EBLC algorithms across various scientific da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23497v1-abstract-full').style.display = 'inline'; document.getElementById('2410.23497v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.23497v1-abstract-full" style="display: none;"> Modern scientific simulations generate massive volumes of data, creating significant challenges for I/O and storage systems. Error-bounded lossy compression (EBLC) offers a solution by reducing dataset sizes while preserving data quality within user-specified limits. This study provides the first comprehensive energy characterization of state-of-the-art EBLC algorithms across various scientific datasets, CPU architectures, and operational modes. We analyze the energy consumption patterns of compression and decompression operations, as well as the energy trade-offs in data I/O scenarios. Our findings demonstrate that EBLC can significantly reduce I/O energy consumption, with savings of up to two orders of magnitude compared to uncompressed I/O for large datasets. In multi-node HPC environments, we observe energy reductions of approximately 25% when using EBLC. We also show that EBLC can achieve compression ratios of 10-100x, potentially reducing storage device requirements by nearly two orders of magnitude. Our work demonstrates the relationships between compression ratios, energy efficiency, and data quality, highlighting the importance of considering compressors and error bounds for specific use cases. Based on our results, we estimate that large-scale HPC facilities could save nearly two orders of magnitude the energy on data writing and significantly reduce storage requirements by integrating EBLC into their I/O subsystems. This work provides a framework for system operators and computational scientists to make informed decisions about implementing EBLC for energy-efficient data management in HPC environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.23497v1-abstract-full').style.display = 'none'; document.getElementById('2410.23497v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17116">arXiv:2410.17116</a> <span> [<a href="https://arxiv.org/pdf/2410.17116">pdf</a>, <a href="https://arxiv.org/format/2410.17116">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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/DFT63277.2024.10753548">10.1109/DFT63277.2024.10753548 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Security and RAS in the Computing Continuum </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Alonso%2C+M">Mart铆 Alonso</a>, <a href="/search/cs?searchtype=author&query=Andreu%2C+D">David Andreu</a>, <a href="/search/cs?searchtype=author&query=Canal%2C+R">Ramon Canal</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a>, <a href="/search/cs?searchtype=author&query=Chatzopoulos%2C+O">Odysseas Chatzopoulos</a>, <a href="/search/cs?searchtype=author&query=Chenet%2C+C">Cristiano Chenet</a>, <a href="/search/cs?searchtype=author&query=Costa%2C+J">Juanjo Costa</a>, <a href="/search/cs?searchtype=author&query=Girones%2C+A">Andreu Girones</a>, <a href="/search/cs?searchtype=author&query=Gizopoulos%2C+D">Dimitris Gizopoulos</a>, <a href="/search/cs?searchtype=author&query=Papadimitriou%2C+G">George Papadimitriou</a>, <a href="/search/cs?searchtype=author&query=Morancho%2C+E">Enric Morancho</a>, <a href="/search/cs?searchtype=author&query=Otero%2C+B">Beatriz Otero</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17116v1-abstract-short" style="display: inline;"> Security and RAS are two non-functional requirements under focus for current systems developed for the computing continuum. Due to the increased number of interconnected computer systems across the continuum, security becomes especially pervasive at all levels, from the smallest edge device to the high-performance cloud at the other end. Similarly, RAS (Reliability, Availability, and Serviceabilit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17116v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17116v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17116v1-abstract-full" style="display: none;"> Security and RAS are two non-functional requirements under focus for current systems developed for the computing continuum. Due to the increased number of interconnected computer systems across the continuum, security becomes especially pervasive at all levels, from the smallest edge device to the high-performance cloud at the other end. Similarly, RAS (Reliability, Availability, and Serviceability) ensures the robustness of a system towards hardware defects. Namely, making them reliable, with high availability and design for easy service. In this paper and as a result of the Vitamin-V EU project, the authors detail the comprehensive approach to malware and hardware attack detection; as well as, the RAS features envisioned for future systems across the computing continuum. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17116v1-abstract-full').style.display = 'none'; document.getElementById('2410.17116v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.11142">arXiv:2410.11142</a> <span> [<a href="https://arxiv.org/pdf/2410.11142">pdf</a>, <a href="https://arxiv.org/format/2410.11142">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> DGRO: Diameter-Guided Ring Optimization for Integrated Research Infrastructure Membership </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shixun Wu</a>, <a href="/search/cs?searchtype=author&query=Raghavan%2C+K">Krishnan Raghavan</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zizhong Chen</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.11142v1-abstract-short" style="display: inline;"> Logical ring is a core component in membership protocol. However, the logic ring fails to consider the underlying physical latency, resulting in a high diameter. To address this issue, we introduce Diameter-Guided Ring Optimization (DGRO), which focuses on constructing rings with the smallest possible diameter, selecting the most effective ring configurations, and implementing these configurations… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11142v1-abstract-full').style.display = 'inline'; document.getElementById('2410.11142v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11142v1-abstract-full" style="display: none;"> Logical ring is a core component in membership protocol. However, the logic ring fails to consider the underlying physical latency, resulting in a high diameter. To address this issue, we introduce Diameter-Guided Ring Optimization (DGRO), which focuses on constructing rings with the smallest possible diameter, selecting the most effective ring configurations, and implementing these configurations in parallel. We first explore an integration of deep Q-learning and graph embedding to optimize the ring topology. We next propose a ring selection strategy that assesses the current topology's average latency against a global benchmark, facilitating integration into modern peer-to-peer protocols and substantially reducing network diameter. To further enhance scalability, we propose a parallel strategy that distributes the topology construction process into separate partitions simultaneously. Our experiment shows that: 1) DGRO efficiently constructs a network topology that achieves up to a 60% reduction in diameter compared to the best results from an extensive search over $10^5$ topologies, all within a significantly shorter computation time, 2) the ring selection of DGRO reduces the diameter of state-of-the-art methods Chord, RAPID, and Perigee by 10%-40%, 44%, and 60%. 3) the parallel construction can scale up to $32$ partitions while maintaining the same diameter compared to the centralized version. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11142v1-abstract-full').style.display = 'none'; document.getElementById('2410.11142v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.15468">arXiv:2409.15468</a> <span> [<a href="https://arxiv.org/pdf/2409.15468">pdf</a>, <a href="https://arxiv.org/format/2409.15468">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> </div> </div> <p class="title is-5 mathjax"> FRSZ2 for In-Register Block Compression Inside GMRES on GPUs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gr%C3%BCtzmacher%2C+T">Thomas Gr眉tzmacher</a>, <a href="/search/cs?searchtype=author&query=Underwood%2C+R">Robert Underwood</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</a>, <a href="/search/cs?searchtype=author&query=Anzt%2C+H">Hartwig Anzt</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="2409.15468v1-abstract-short" style="display: inline;"> The performance of the GMRES iterative solver on GPUs is limited by the GPU main memory bandwidth. Compressed Basis GMRES outperforms GMRES by storing the Krylov basis in low precision, thereby reducing the memory access. An open question is whether compression techniques that are more sophisticated than casting to low precision can enable large runtime savings while preserving the accuracy of the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15468v1-abstract-full').style.display = 'inline'; document.getElementById('2409.15468v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15468v1-abstract-full" style="display: none;"> The performance of the GMRES iterative solver on GPUs is limited by the GPU main memory bandwidth. Compressed Basis GMRES outperforms GMRES by storing the Krylov basis in low precision, thereby reducing the memory access. An open question is whether compression techniques that are more sophisticated than casting to low precision can enable large runtime savings while preserving the accuracy of the final results. This paper presents the lightweight in-register compressor FRSZ2 that can decompress at the bandwidth speed of a modern NVIDIA H100 GPU. In an experimental evaluation, we demonstrate using FRSZ2 instead of low precision for compression of the Krylov basis can bring larger runtime benefits without impacting final accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15468v1-abstract-full').style.display = 'none'; document.getElementById('2409.15468v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14816">arXiv:2409.14816</a> <span> [<a href="https://arxiv.org/pdf/2409.14816">pdf</a>, <a href="https://arxiv.org/format/2409.14816">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div 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/10.1145/3649329.3655691">10.1145/3649329.3655691 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> VARADE: a Variational-based AutoRegressive model for Anomaly Detection on the Edge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mascolini%2C+A">Alessio Mascolini</a>, <a href="/search/cs?searchtype=author&query=Gaiardelli%2C+S">Sebastiano Gaiardelli</a>, <a href="/search/cs?searchtype=author&query=Ponzio%2C+F">Francesco Ponzio</a>, <a href="/search/cs?searchtype=author&query=Dall%27Ora%2C+N">Nicola Dall'Ora</a>, <a href="/search/cs?searchtype=author&query=Macii%2C+E">Enrico Macii</a>, <a href="/search/cs?searchtype=author&query=Vinco%2C+S">Sara Vinco</a>, <a href="/search/cs?searchtype=author&query=Di+Cataldo%2C+S">Santa Di Cataldo</a>, <a href="/search/cs?searchtype=author&query=Fummi%2C+F">Franco Fummi</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="2409.14816v2-abstract-short" style="display: inline;"> Detecting complex anomalies on massive amounts of data is a crucial task in Industry 4.0, best addressed by deep learning. However, available solutions are computationally demanding, requiring cloud architectures prone to latency and bandwidth issues. This work presents VARADE, a novel solution implementing a light autoregressive framework based on variational inference, which is best suited for r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14816v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14816v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14816v2-abstract-full" style="display: none;"> Detecting complex anomalies on massive amounts of data is a crucial task in Industry 4.0, best addressed by deep learning. However, available solutions are computationally demanding, requiring cloud architectures prone to latency and bandwidth issues. This work presents VARADE, a novel solution implementing a light autoregressive framework based on variational inference, which is best suited for real-time execution on the edge. The proposed approach was validated on a robotic arm, part of a pilot production line, and compared with several state-of-the-art algorithms, obtaining the best trade-off between anomaly detection accuracy, power consumption and inference frequency on two different edge platforms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14816v2-abstract-full').style.display = 'none'; document.getElementById('2409.14816v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.03500">arXiv:2409.03500</a> <span> [<a href="https://arxiv.org/pdf/2409.03500">pdf</a>, <a href="https://arxiv.org/format/2409.03500">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Willingness to Read AI-Generated News Is Not Driven by Their Perceived Quality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gilardi%2C+F">Fabrizio Gilardi</a>, <a href="/search/cs?searchtype=author&query=Di+Lorenzo%2C+S">Sabrina Di Lorenzo</a>, <a href="/search/cs?searchtype=author&query=Ezzaini%2C+J">Juri Ezzaini</a>, <a href="/search/cs?searchtype=author&query=Santa%2C+B">Beryl Santa</a>, <a href="/search/cs?searchtype=author&query=Streiff%2C+B">Benjamin Streiff</a>, <a href="/search/cs?searchtype=author&query=Zurfluh%2C+E">Eric Zurfluh</a>, <a href="/search/cs?searchtype=author&query=Hoes%2C+E">Emma Hoes</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="2409.03500v3-abstract-short" style="display: inline;"> The advancement of artificial intelligence has led to its application in many areas, including news media, which makes it crucial to understand public reception of AI-generated news. This preregistered study investigates (i) the perceived quality of AI-assisted and AI-generated versus human-generated news articles, (ii) whether disclosure of AI's involvement in generating these news articles influ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03500v3-abstract-full').style.display = 'inline'; document.getElementById('2409.03500v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03500v3-abstract-full" style="display: none;"> The advancement of artificial intelligence has led to its application in many areas, including news media, which makes it crucial to understand public reception of AI-generated news. This preregistered study investigates (i) the perceived quality of AI-assisted and AI-generated versus human-generated news articles, (ii) whether disclosure of AI's involvement in generating these news articles influences engagement with them, and (iii) whether such awareness affects the willingness to read AI-generated articles in the future. We conducted a survey experiment with 599 Swiss participants, who evaluated the credibility, readability, and expertise of news articles either written by journalists (control group), rewritten by AI (AI-assisted group), or entirely written by AI (AI-generated group). Our results indicate that all articles were perceived to be of equal quality. When participants in the treatment groups were subsequently made aware of AI's role, they expressed a higher willingness to continue reading the articles than participants in the control group. However, they were not more willing to read AI-generated news in the future. These results suggest that aversion to AI usage in news media is not primarily rooted in a perceived lack of quality, and that by disclosing using AI, journalists could induce more short-term engagement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03500v3-abstract-full').style.display = 'none'; document.getElementById('2409.03500v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.02618">arXiv:2409.02618</a> <span> [<a href="https://arxiv.org/pdf/2409.02618">pdf</a>, <a href="https://arxiv.org/format/2409.02618">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> </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/BioCAS61083.2024.10798178">10.1109/BioCAS61083.2024.10798178 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Neuromorphic Heart Rate Monitors: Neural State Machines for Monotonic Change Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Carpegna%2C+A">Alessio Carpegna</a>, <a href="/search/cs?searchtype=author&query=De+Luca%2C+C">Chiara De Luca</a>, <a href="/search/cs?searchtype=author&query=Pozzi%2C+F+E">Federico Emanuele Pozzi</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a>, <a href="/search/cs?searchtype=author&query=Indiveri%2C+G">Giacomo Indiveri</a>, <a href="/search/cs?searchtype=author&query=Donati%2C+E">Elisa Donati</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="2409.02618v1-abstract-short" style="display: inline;"> Detecting monotonic changes in heart rate (HR) is crucial for early identification of cardiac conditions and health management. This is particularly important for dementia patients, where HR trends can signal stress or agitation. Developing wearable technologies that can perform always-on monitoring of HRs is essential to effectively detect slow changes over extended periods of time. However, desi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02618v1-abstract-full').style.display = 'inline'; document.getElementById('2409.02618v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02618v1-abstract-full" style="display: none;"> Detecting monotonic changes in heart rate (HR) is crucial for early identification of cardiac conditions and health management. This is particularly important for dementia patients, where HR trends can signal stress or agitation. Developing wearable technologies that can perform always-on monitoring of HRs is essential to effectively detect slow changes over extended periods of time. However, designing compact electronic circuits that can monitor and process bio-signals continuously, and that can operate in a low-power regime to ensure long-lasting performance, is still an open challenge. Neuromorphic technology offers an energy-efficient solution for real-time health monitoring. We propose a neuromorphic implementation of a Neural State Machine (NSM) network to encode different health states and switch between them based on the input stimuli. Our focus is on detecting monotonic state switches in electrocardiogram data to identify progressive HR increases. This innovative approach promises significant advancements in continuous health monitoring and management. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02618v1-abstract-full').style.display = 'none'; document.getElementById('2409.02618v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE 30th International Symposium on On-Line Testing and Robust System Design (IOLTS) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14469">arXiv:2408.14469</a> <span> [<a href="https://arxiv.org/pdf/2408.14469">pdf</a>, <a href="https://arxiv.org/format/2408.14469">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Q">Qirui Chen</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Shangzhe Di</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+W">Weidi Xie</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="2408.14469v1-abstract-short" style="display: inline;"> This paper considers the problem of Multi-Hop Video Question Answering (MH-VidQA) in long-form egocentric videos. This task not only requires to answer visual questions, but also to localize multiple relevant time intervals within the video as visual evidences. We develop an automated pipeline to create multi-hop question-answering pairs with associated temporal evidence, enabling to construct a l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14469v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14469v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14469v1-abstract-full" style="display: none;"> This paper considers the problem of Multi-Hop Video Question Answering (MH-VidQA) in long-form egocentric videos. This task not only requires to answer visual questions, but also to localize multiple relevant time intervals within the video as visual evidences. We develop an automated pipeline to create multi-hop question-answering pairs with associated temporal evidence, enabling to construct a large-scale dataset for instruction-tuning. To monitor the progress of this new task, we further curate a high-quality benchmark, MultiHop-EgoQA, with careful manual verification and refinement. Experimental results reveal that existing multi-modal systems exhibit inadequate multi-hop grounding and reasoning abilities, resulting in unsatisfactory performance. We then propose a novel architecture, termed as Grounding Scattered Evidence with Large Language Model (GeLM), that enhances multi-modal large language models (MLLMs) by incorporating a grounding module to retrieve temporal evidence from videos using flexible grounding tokens. Trained on our visual instruction data, GeLM demonstrates improved multi-hop grounding and reasoning capabilities, setting a new baseline for this challenging task. Furthermore, when trained on third-person view videos, the same architecture also achieves state-of-the-art performance on the single-hop VidQA benchmark, ActivityNet-RTL, demonstrating its effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14469v1-abstract-full').style.display = 'none'; document.getElementById('2408.14469v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14090">arXiv:2408.14090</a> <span> [<a href="https://arxiv.org/pdf/2408.14090">pdf</a>, <a href="https://arxiv.org/format/2408.14090">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</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/SC41406.2024.00039">10.1109/SC41406.2024.00039 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Exploring GPU-to-GPU Communication: Insights into Supercomputer Interconnects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=De+Sensi%2C+D">Daniele De Sensi</a>, <a href="/search/cs?searchtype=author&query=Pichetti%2C+L">Lorenzo Pichetti</a>, <a href="/search/cs?searchtype=author&query=Vella%2C+F">Flavio Vella</a>, <a href="/search/cs?searchtype=author&query=De+Matteis%2C+T">Tiziano De Matteis</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+Z">Zebin Ren</a>, <a href="/search/cs?searchtype=author&query=Fusco%2C+L">Luigi Fusco</a>, <a href="/search/cs?searchtype=author&query=Turisini%2C+M">Matteo Turisini</a>, <a href="/search/cs?searchtype=author&query=Cesarini%2C+D">Daniele Cesarini</a>, <a href="/search/cs?searchtype=author&query=Lust%2C+K">Kurt Lust</a>, <a href="/search/cs?searchtype=author&query=Trivedi%2C+A">Animesh Trivedi</a>, <a href="/search/cs?searchtype=author&query=Roweth%2C+D">Duncan Roweth</a>, <a href="/search/cs?searchtype=author&query=Spiga%2C+F">Filippo Spiga</a>, <a href="/search/cs?searchtype=author&query=Di+Girolamo%2C+S">Salvatore Di Girolamo</a>, <a href="/search/cs?searchtype=author&query=Hoefler%2C+T">Torsten Hoefler</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="2408.14090v2-abstract-short" style="display: inline;"> Multi-GPU nodes are increasingly common in the rapidly evolving landscape of exascale supercomputers. On these systems, GPUs on the same node are connected through dedicated networks, with bandwidths up to a few terabits per second. However, gauging performance expectations and maximizing system efficiency is challenging due to different technologies, design options, and software layers. This pape… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14090v2-abstract-full').style.display = 'inline'; document.getElementById('2408.14090v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14090v2-abstract-full" style="display: none;"> Multi-GPU nodes are increasingly common in the rapidly evolving landscape of exascale supercomputers. On these systems, GPUs on the same node are connected through dedicated networks, with bandwidths up to a few terabits per second. However, gauging performance expectations and maximizing system efficiency is challenging due to different technologies, design options, and software layers. This paper comprehensively characterizes three supercomputers - Alps, Leonardo, and LUMI - each with a unique architecture and design. We focus on performance evaluation of intra-node and inter-node interconnects on up to 4096 GPUs, using a mix of intra-node and inter-node benchmarks. By analyzing its limitations and opportunities, we aim to offer practical guidance to researchers, system architects, and software developers dealing with multi-GPU supercomputing. Our results show that there is untapped bandwidth, and there are still many opportunities for optimization, ranging from network to software optimization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14090v2-abstract-full').style.display = 'none'; document.getElementById('2408.14090v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 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">ACM Class:</span> C.2.4; C.5.1; C.2.1; C.4 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Published in Proceedings of The International Conference for High Performance Computing Networking, Storage, and Analysis (SC '24) (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13356">arXiv:2408.13356</a> <span> [<a href="https://arxiv.org/pdf/2408.13356">pdf</a>, <a href="https://arxiv.org/format/2408.13356">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Network-Offloaded Bandwidth-Optimal Broadcast and Allgather for Distributed AI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khalilov%2C+M">Mikhail Khalilov</a>, <a href="/search/cs?searchtype=author&query=Di+Girolamo%2C+S">Salvatore Di Girolamo</a>, <a href="/search/cs?searchtype=author&query=Chrapek%2C+M">Marcin Chrapek</a>, <a href="/search/cs?searchtype=author&query=Nudelman%2C+R">Rami Nudelman</a>, <a href="/search/cs?searchtype=author&query=Bloch%2C+G">Gil Bloch</a>, <a href="/search/cs?searchtype=author&query=Hoefler%2C+T">Torsten Hoefler</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="2408.13356v2-abstract-short" style="display: inline;"> In the Fully Sharded Data Parallel (FSDP) training pipeline, collective operations can be interleaved to maximize the communication/computation overlap. In this scenario, outstanding operations such as Allgather and Reduce-Scatter can compete for the injection bandwidth and create pipeline bubbles. To address this problem, we propose a novel bandwidth-optimal Allgather collective algorithm that le… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13356v2-abstract-full').style.display = 'inline'; document.getElementById('2408.13356v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13356v2-abstract-full" style="display: none;"> In the Fully Sharded Data Parallel (FSDP) training pipeline, collective operations can be interleaved to maximize the communication/computation overlap. In this scenario, outstanding operations such as Allgather and Reduce-Scatter can compete for the injection bandwidth and create pipeline bubbles. To address this problem, we propose a novel bandwidth-optimal Allgather collective algorithm that leverages hardware multicast. We use multicast to build a constant-time reliable Broadcast protocol, a building block for constructing an optimal Allgather schedule. Our Allgather algorithm achieves 2x traffic reduction on a 188-node testbed. To free the host side from running the protocol, we employ SmartNIC offloading. We extract the parallelism in our Allgather algorithm and map it to a SmartNIC specialized for hiding the cost of data movement. We show that our SmartNIC-offloaded collective progress engine can scale to the next generation of 1.6 Tbit/s links. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13356v2-abstract-full').style.display = 'none'; document.getElementById('2408.13356v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.11971">arXiv:2408.11971</a> <span> [<a href="https://arxiv.org/pdf/2408.11971">pdf</a>, <a href="https://arxiv.org/format/2408.11971">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> HoSZp: An Efficient Homomorphic Error-bounded Lossy Compressor for Scientific Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Agarwal%2C+T">Tripti Agarwal</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yafan Huang</a>, <a href="/search/cs?searchtype=author&query=Gopalakrishnan%2C+G">Ganesh Gopalakrishnan</a>, <a href="/search/cs?searchtype=author&query=Underwood%2C+R">Robert Underwood</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kai Zhao</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xin Liang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Guanpeng Li</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</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="2408.11971v1-abstract-short" style="display: inline;"> Error-bounded lossy compression has been a critical technique to significantly reduce the sheer amounts of simulation datasets for high-performance computing (HPC) scientific applications while effectively controlling the data distortion based on user-specified error bound. In many real-world use cases, users must perform computational operations on the compressed data (a.k.a. homomorphic compress… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11971v1-abstract-full').style.display = 'inline'; document.getElementById('2408.11971v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.11971v1-abstract-full" style="display: none;"> Error-bounded lossy compression has been a critical technique to significantly reduce the sheer amounts of simulation datasets for high-performance computing (HPC) scientific applications while effectively controlling the data distortion based on user-specified error bound. In many real-world use cases, users must perform computational operations on the compressed data (a.k.a. homomorphic compression). However, none of the existing error-bounded lossy compressors support the homomorphism, inevitably resulting in undesired decompression costs. In this paper, we propose a novel homomorphic error-bounded lossy compressor (called HoSZp), which supports not only error-bounding features but efficient computations (including negation, addition, multiplication, mean, variance, etc.) on the compressed data without the complete decompression step, which is the first attempt to the best of our knowledge. We develop several optimization strategies to maximize the overall compression ratio and execution performance. We evaluate HoSZp compared to other state-of-the-art lossy compressors based on multiple real-world scientific application datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11971v1-abstract-full').style.display = 'none'; document.getElementById('2408.11971v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 August, 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">12 pages, 7 figures, 9 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.06743">arXiv:2408.06743</a> <span> [<a href="https://arxiv.org/pdf/2408.06743">pdf</a>, <a href="https://arxiv.org/format/2408.06743">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"> Class-aware and Augmentation-free Contrastive Learning from Label Proportion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jialiang Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+N">Ning Zhang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Shimin Di</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ruidong Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Lei Chen</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="2408.06743v1-abstract-short" style="display: inline;"> Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user modeling and personalization, where user privacy is paramount, offering insights into user preferences without revealing individual data. LLP faces a unique diffi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06743v1-abstract-full').style.display = 'inline'; document.getElementById('2408.06743v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.06743v1-abstract-full" style="display: none;"> Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user modeling and personalization, where user privacy is paramount, offering insights into user preferences without revealing individual data. LLP faces a unique difficulty: the misalignment between bag-level supervision and the objective of instance-level prediction, primarily due to the inherent ambiguity in label proportion matching. Previous studies have demonstrated deep representation learning can generate auxiliary signals to promote the supervision level in the image domain. However, applying these techniques to tabular data presents significant challenges: 1) they rely heavily on label-invariant augmentation to establish multi-view, which is not feasible with the heterogeneous nature of tabular datasets, and 2) tabular datasets often lack sufficient semantics for perfect class distinction, making them prone to suboptimality caused by the inherent ambiguity of label proportion matching. To address these challenges, we propose an augmentation-free contrastive framework TabLLP-BDC that introduces class-aware supervision (explicitly aware of class differences) at the instance level. Our solution features a two-stage Bag Difference Contrastive (BDC) learning mechanism that establishes robust class-aware instance-level supervision by disassembling the nuance between bag label proportions, without relying on augmentations. Concurrently, our model presents a pioneering multi-task pretraining pipeline tailored for tabular-based LLP, capturing intrinsic tabular feature correlations in alignment with label proportion distribution. Extensive experiments demonstrate that TabLLP-BDC achieves state-of-the-art performance for LLP in the tabular domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06743v1-abstract-full').style.display = 'none'; document.getElementById('2408.06743v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.06717">arXiv:2408.06717</a> <span> [<a href="https://arxiv.org/pdf/2408.06717">pdf</a>, <a href="https://arxiv.org/format/2408.06717">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Computation-friendly Graph Neural Network Design by Accumulating Knowledge on Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jialiang Wang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Shimin Di</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hanmo Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhili Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiachuan Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Lei Chen</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+X">Xiaofang Zhou</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="2408.06717v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs), like other neural networks, have shown remarkable success but are hampered by the complexity of their architecture designs, which heavily depend on specific data and tasks. Traditionally, designing proper architectures involves trial and error, which requires intensive manual effort to optimize various components. To reduce human workload, researchers try to develop a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06717v1-abstract-full').style.display = 'inline'; document.getElementById('2408.06717v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.06717v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs), like other neural networks, have shown remarkable success but are hampered by the complexity of their architecture designs, which heavily depend on specific data and tasks. Traditionally, designing proper architectures involves trial and error, which requires intensive manual effort to optimize various components. To reduce human workload, researchers try to develop automated algorithms to design GNNs. However, both experts and automated algorithms suffer from two major issues in designing GNNs: 1) the substantial computational resources expended in repeatedly trying candidate GNN architectures until a feasible design is achieved, and 2) the intricate and prolonged processes required for humans or algorithms to accumulate knowledge of the interrelationship between graphs, GNNs, and performance. To further enhance the automation of GNN architecture design, we propose a computation-friendly way to empower Large Language Models (LLMs) with specialized knowledge in designing GNNs, thereby drastically shortening the computational overhead and development cycle of designing GNN architectures. Our framework begins by establishing a knowledge retrieval pipeline that comprehends the intercorrelations between graphs, GNNs, and performance. This pipeline converts past model design experiences into structured knowledge for LLM reference, allowing it to quickly suggest initial model proposals. Subsequently, we introduce a knowledge-driven search strategy that emulates the exploration-exploitation process of human experts, enabling quick refinement of initial proposals within a promising scope. Extensive experiments demonstrate that our framework can efficiently deliver promising (e.g., Top-5.77%) initial model proposals for unseen datasets within seconds and without any prior training and achieve outstanding search performance in a few iterations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06717v1-abstract-full').style.display = 'none'; document.getElementById('2408.06717v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.01391">arXiv:2408.01391</a> <span> [<a href="https://arxiv.org/pdf/2408.01391">pdf</a>, <a href="https://arxiv.org/format/2408.01391">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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"> FT K-means: A High-Performance K-means on GPU with Fault Tolerance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shixun Wu</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+Y">Yitong Ding</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+Y">Yujia Zhai</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Jian%2C+Z">Zizhe Jian</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+H">Huangliang Dai</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Wong%2C+B+M">Bryan M. Wong</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zizhong Chen</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</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="2408.01391v2-abstract-short" style="display: inline;"> K-means is a widely used algorithm in clustering, however, its efficiency is primarily constrained by the computational cost of distance computing. Existing implementations suffer from suboptimal utilization of computational units and lack resilience against soft errors. To address these challenges, we introduce FT K-means, a high-performance GPU-accelerated implementation of K-means with online f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01391v2-abstract-full').style.display = 'inline'; document.getElementById('2408.01391v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01391v2-abstract-full" style="display: none;"> K-means is a widely used algorithm in clustering, however, its efficiency is primarily constrained by the computational cost of distance computing. Existing implementations suffer from suboptimal utilization of computational units and lack resilience against soft errors. To address these challenges, we introduce FT K-means, a high-performance GPU-accelerated implementation of K-means with online fault tolerance. We first present a stepwise optimization strategy that achieves competitive performance compared to NVIDIA's cuML library. We further improve FT K-means with a template-based code generation framework that supports different data types and adapts to different input shapes. A novel warp-level tensor-core error correction scheme is proposed to address the failure of existing fault tolerance methods due to memory asynchronization during copy operations. Our experimental evaluations on NVIDIA T4 GPU and A100 GPU demonstrate that FT K-means without fault tolerance outperforms cuML's K-means implementation, showing a performance increase of 10\%-300\% in scenarios involving irregular data shapes. Moreover, the fault tolerance feature of FT K-means introduces only an overhead of 11\%, maintaining robust performance even with tens of errors injected per second. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01391v2-abstract-full').style.display = 'none'; document.getElementById('2408.01391v2-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.07599">arXiv:2407.07599</a> <span> [<a href="https://arxiv.org/pdf/2407.07599">pdf</a>, <a href="https://arxiv.org/format/2407.07599">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> <div 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/IOLTS60994.2024.10616053">10.1109/IOLTS60994.2024.10616053 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Can social media shape the security of next-generation connected vehicles? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Scarano%2C+N">Nicola Scarano</a>, <a href="/search/cs?searchtype=author&query=Mannella%2C+L">Luca Mannella</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.07599v1-abstract-short" style="display: inline;"> The increasing adoption of connectivity and electronic components in vehicles makes these systems valuable targets for attackers. While automotive vendors prioritize safety, there remains a critical need for comprehensive assessment and analysis of cyber risks. In this context, this paper proposes a Social Media Automotive Threat Intelligence (SOCMATI) framework, specifically designed for the emer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07599v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07599v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07599v1-abstract-full" style="display: none;"> The increasing adoption of connectivity and electronic components in vehicles makes these systems valuable targets for attackers. While automotive vendors prioritize safety, there remains a critical need for comprehensive assessment and analysis of cyber risks. In this context, this paper proposes a Social Media Automotive Threat Intelligence (SOCMATI) framework, specifically designed for the emerging field of automotive cybersecurity. The framework leverages advanced intelligence techniques and machine learning models to extract valuable insights from social media. Four use cases illustrate the framework's potential by demonstrating how it can significantly enhance threat assessment procedures within the automotive industry. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07599v1-abstract-full').style.display = 'none'; document.getElementById('2407.07599v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Position paper, four pages, two images</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE 30th International Symposium on On-Line Testing and Robust System Design (IOLTS) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.03111">arXiv:2407.03111</a> <span> [<a href="https://arxiv.org/pdf/2407.03111">pdf</a>, <a href="https://arxiv.org/format/2407.03111">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</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/10.1109/ISVLSI61997.2024.00052">10.1109/ISVLSI61997.2024.00052 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dequino%2C+A">Alberto Dequino</a>, <a href="/search/cs?searchtype=author&query=Carpegna%2C+A">Alessio Carpegna</a>, <a href="/search/cs?searchtype=author&query=Nadalini%2C+D">Davide Nadalini</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Benini%2C+L">Luca Benini</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a>, <a href="/search/cs?searchtype=author&query=Conti%2C+F">Francesco Conti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.03111v2-abstract-short" style="display: inline;"> Rehearsal-based Continual Learning (CL) has been intensely investigated in Deep Neural Networks (DNNs). However, its application in Spiking Neural Networks (SNNs) has not been explored in depth. In this paper we introduce the first memory-efficient implementation of Latent Replay (LR)-based CL for SNNs, designed to seamlessly integrate with resource-constrained devices. LRs combine new samples wit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03111v2-abstract-full').style.display = 'inline'; document.getElementById('2407.03111v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.03111v2-abstract-full" style="display: none;"> Rehearsal-based Continual Learning (CL) has been intensely investigated in Deep Neural Networks (DNNs). However, its application in Spiking Neural Networks (SNNs) has not been explored in depth. In this paper we introduce the first memory-efficient implementation of Latent Replay (LR)-based CL for SNNs, designed to seamlessly integrate with resource-constrained devices. LRs combine new samples with latent representations of previously learned data, to mitigate forgetting. Experiments on the Heidelberg SHD dataset with Sample and Class-Incremental tasks reach a Top-1 accuracy of 92.5% and 92%, respectively, without forgetting the previously learned information. Furthermore, we minimize the LRs' requirements by applying a time-domain compression, reducing by two orders of magnitude their memory requirement, with respect to a naive rehearsal setup, with a maximum accuracy drop of 4%. On a Multi-Class-Incremental task, our SNN learns 10 new classes from an initial set of 10, reaching a Top-1 accuracy of 78.4% on the full test set. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03111v2-abstract-full').style.display = 'none'; document.getElementById('2407.03111v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.00483">arXiv:2407.00483</a> <span> [<a href="https://arxiv.org/pdf/2407.00483">pdf</a>, <a href="https://arxiv.org/format/2407.00483">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </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/IOLTS60994.2024.10616052">10.1109/IOLTS60994.2024.10616052 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Navigating the road to automotive cybersecurity compliance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Oberti%2C+F">Franco Oberti</a>, <a href="/search/cs?searchtype=author&query=Abrate%2C+F">Fabrizio Abrate</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Parisi%2C+F">Filippo Parisi</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.00483v1-abstract-short" style="display: inline;"> The automotive industry has evolved significantly since the introduction of the Ford Model T in 1908. Today's vehicles are not merely mechanical constructs; they are integral components of a complex digital ecosystem, equipped with advanced connectivity features powered by Artificial Intelligence and cloud computing technologies. This evolution has enhanced vehicle safety, efficiency, and the over… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00483v1-abstract-full').style.display = 'inline'; document.getElementById('2407.00483v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.00483v1-abstract-full" style="display: none;"> The automotive industry has evolved significantly since the introduction of the Ford Model T in 1908. Today's vehicles are not merely mechanical constructs; they are integral components of a complex digital ecosystem, equipped with advanced connectivity features powered by Artificial Intelligence and cloud computing technologies. This evolution has enhanced vehicle safety, efficiency, and the overall driving experience. However, it also introduces new challenges, notably in cybersecurity. With the increasing integration of digital technologies, vehicles have become more susceptible to cyber-attacks, prompting significant cybersecurity concerns. These concerns include securing sensitive data, protecting vehicles from unauthorized access, and ensuring user privacy. In response, the automotive industry is compelled to adopt robust cybersecurity measures to safeguard both vehicles and data against potential threats. Legislative frameworks such as UNR155 and UNR156 by the United Nations, along with other international regulations, aim to establish stringent cybersecurity mandates. These regulations require compliance with comprehensive cybersecurity management systems and necessitate regular updates and testing to cope with the evolving nature of cyber threats. The introduction of such regulations highlights the growing recognition of cybersecurity as a critical component of automotive safety and functionality. The future of automotive cybersecurity lies in the continuous development of advanced protective measures and collaborative efforts among all stakeholders, including manufacturers, policymakers, and cybersecurity professionals. Only through such concerted efforts can the industry hope to address the dual goals of innovation in vehicle functionality and stringent security measures against the backdrop of an increasingly interconnected digital landscape. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00483v1-abstract-full').style.display = 'none'; document.getElementById('2407.00483v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE 30th International Symposium on On-Line Testing and Robust System Design (IOLTS) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.00052">arXiv:2407.00052</a> <span> [<a href="https://arxiv.org/pdf/2407.00052">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Vitamin-V: Expanding Open-Source RISC-V Cloud Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Canal%2C+R">Ramon Canal</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a>, <a href="/search/cs?searchtype=author&query=Gizopoulos%2C+D">Dimitris Gizopoulos</a>, <a href="/search/cs?searchtype=author&query=Scionti%2C+A">Alberto Scionti</a>, <a href="/search/cs?searchtype=author&query=Lubrano%2C+F">Francesco Lubrano</a>, <a href="/search/cs?searchtype=author&query=Berral%2C+J">Josep-Llu铆s Berral</a>, <a href="/search/cs?searchtype=author&query=Call%2C+A">Aaron Call</a>, <a href="/search/cs?searchtype=author&query=Marron%2C+D">Diego Marron</a>, <a href="/search/cs?searchtype=author&query=Nikas%2C+K">Konstantinos Nikas</a>, <a href="/search/cs?searchtype=author&query=Pnevmatikatos%2C+D">Dionisios Pnevmatikatos</a>, <a href="/search/cs?searchtype=author&query=Raho%2C+D">Daniel Raho</a>, <a href="/search/cs?searchtype=author&query=Rigo%2C+A">Alvise Rigo</a>, <a href="/search/cs?searchtype=author&query=Papaefstathiou%2C+Y">Yannis Papaefstathiou</a>, <a href="/search/cs?searchtype=author&query=Arnau%2C+J+M">Jos茅 Mar铆a Arnau</a>, <a href="/search/cs?searchtype=author&query=Arelakis%2C+A">Angelos Arelakis</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.00052v1-abstract-short" style="display: inline;"> Among the key contributions of Vitamin-V (2023-2025 Horizon Europe project), we develop a complete RISC-V open-source software stack for cloud services with comparable performance to the cloud-dominant x86 counterpart. In this paper, we detail the software suites and applications ported plus the three cloud setups under evaluation. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.00052v1-abstract-full" style="display: none;"> Among the key contributions of Vitamin-V (2023-2025 Horizon Europe project), we develop a complete RISC-V open-source software stack for cloud services with comparable performance to the cloud-dominant x86 counterpart. In this paper, we detail the software suites and applications ported plus the three cloud setups under evaluation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00052v1-abstract-full').style.display = 'none'; document.getElementById('2407.00052v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">RISC-V Summit Europe 2024, 24-28 June 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/2406.10282">arXiv:2406.10282</a> <span> [<a href="https://arxiv.org/pdf/2406.10282">pdf</a>, <a href="https://arxiv.org/format/2406.10282">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Hardware-based stack buffer overflow attack detection on RISC-V architectures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chenet%2C+C+P">Cristiano Pegoraro Chenet</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Ziteng Zhang</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.10282v1-abstract-short" style="display: inline;"> This work evaluates how well hardware-based approaches detect stack buffer overflow (SBO) attacks in RISC-V systems. We conducted simulations on the PULP platform and examined micro-architecture events using semi-supervised anomaly detection techniques. The findings showed the challenge of detection performance. Thus, a potential solution combines software and hardware-based detectors concurrently… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10282v1-abstract-full').style.display = 'inline'; document.getElementById('2406.10282v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10282v1-abstract-full" style="display: none;"> This work evaluates how well hardware-based approaches detect stack buffer overflow (SBO) attacks in RISC-V systems. We conducted simulations on the PULP platform and examined micro-architecture events using semi-supervised anomaly detection techniques. The findings showed the challenge of detection performance. Thus, a potential solution combines software and hardware-based detectors concurrently, with hardware as the primary defense. The hardware-based approaches present compelling benefits that could enhance RISC-V-based architectures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10282v1-abstract-full').style.display = 'none'; document.getElementById('2406.10282v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">2 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.07125">arXiv:2406.07125</a> <span> [<a href="https://arxiv.org/pdf/2406.07125">pdf</a>, <a href="https://arxiv.org/format/2406.07125">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <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/10.1109/ISCC61673.2024.10733705">10.1109/ISCC61673.2024.10733705 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> CARACAS: vehiCular ArchitectuRe for detAiled Can Attacks Simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kirdi%2C+S+M">Sadek Misto Kirdi</a>, <a href="/search/cs?searchtype=author&query=Scarano%2C+N">Nicola Scarano</a>, <a href="/search/cs?searchtype=author&query=Oberti%2C+F">Franco Oberti</a>, <a href="/search/cs?searchtype=author&query=Mannella%2C+L">Luca Mannella</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.07125v1-abstract-short" style="display: inline;"> Modern vehicles are increasingly vulnerable to attacks that exploit network infrastructures, particularly the Controller Area Network (CAN) networks. To effectively counter such threats using contemporary tools like Intrusion Detection Systems (IDSs) based on data analysis and classification, large datasets of CAN messages become imperative. This paper delves into the feasibility of generating syn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07125v1-abstract-full').style.display = 'inline'; document.getElementById('2406.07125v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.07125v1-abstract-full" style="display: none;"> Modern vehicles are increasingly vulnerable to attacks that exploit network infrastructures, particularly the Controller Area Network (CAN) networks. To effectively counter such threats using contemporary tools like Intrusion Detection Systems (IDSs) based on data analysis and classification, large datasets of CAN messages become imperative. This paper delves into the feasibility of generating synthetic datasets by harnessing the modeling capabilities of simulation frameworks such as Simulink coupled with a robust representation of attack models to present CARACAS, a vehicular model, including component control via CAN messages and attack injection capabilities. CARACAS showcases the efficacy of this methodology, including a Battery Electric Vehicle (BEV) model, and focuses on attacks targeting torque control in two distinct scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07125v1-abstract-full').style.display = 'none'; document.getElementById('2406.07125v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 8 figures, TrustAICyberSec workshop - IEEE ISCC 2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 29th IEEE Symposium on Computers and Communications, ISCC 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.06230">arXiv:2406.06230</a> <span> [<a href="https://arxiv.org/pdf/2406.06230">pdf</a>, <a href="https://arxiv.org/format/2406.06230">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> UEMM-Air: Make Unmanned Aerial Vehicles Perform More Multi-modal Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yao%2C+L">Liang Yao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+F">Fan Liu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Shengxiang Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chuanyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xing Ma</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+J">Jianyu Jiang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zequan Wang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Shimin Di</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jun Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.06230v3-abstract-short" style="display: inline;"> The development of multi-modal learning for Unmanned Aerial Vehicles (UAVs) typically relies on a large amount of pixel-aligned multi-modal image data. However, existing datasets face challenges such as limited modalities, high construction costs, and imprecise annotations. To this end, we propose a synthetic multi-modal UAV-based multi-task dataset, UEMM-Air. Specifically, we simulate various UAV… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.06230v3-abstract-full').style.display = 'inline'; document.getElementById('2406.06230v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.06230v3-abstract-full" style="display: none;"> The development of multi-modal learning for Unmanned Aerial Vehicles (UAVs) typically relies on a large amount of pixel-aligned multi-modal image data. However, existing datasets face challenges such as limited modalities, high construction costs, and imprecise annotations. To this end, we propose a synthetic multi-modal UAV-based multi-task dataset, UEMM-Air. Specifically, we simulate various UAV flight scenarios and object types using the Unreal Engine (UE). Then we design the UAV's flight logic to automatically collect data from different scenarios, perspectives, and altitudes. Furthermore, we propose a novel heuristic automatic annotation algorithm to generate accurate object detection labels. Finally, we utilize labels to generate text descriptions of images to make our UEMM-Air support more cross-modality tasks. In total, our UEMM-Air consists of 120k pairs of images with 6 modalities and precise annotations. Moreover, we conduct numerous experiments and establish new benchmark results on our dataset. We also found that models pre-trained on UEMM-Air exhibit better performance on downstream tasks compared to other similar datasets. The dataset is publicly available (https://github.com/1e12Leon/UEMM-Air) to support the research of multi-modal tasks on UAVs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.06230v3-abstract-full').style.display = 'none'; document.getElementById('2406.06230v3-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, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.04227">arXiv:2406.04227</a> <span> [<a href="https://arxiv.org/pdf/2406.04227">pdf</a>, <a href="https://arxiv.org/format/2406.04227">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <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/10.1007/978-981-96-0576-7_21">10.1007/978-981-96-0576-7_21 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> R-CONV: An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eltaras%2C+T+A">Tamer Ahmed Eltaras</a>, <a href="/search/cs?searchtype=author&query=Malluhi%2C+Q">Qutaibah Malluhi</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a>, <a href="/search/cs?searchtype=author&query=Qayyum%2C+A">Adnan Qayyum</a>, <a href="/search/cs?searchtype=author&query=Qadir%2C+J">Junaid Qadir</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.04227v1-abstract-short" style="display: inline;"> In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent studies show that private training data can be leaked through many gradient attacks. While previous analytical-based attacks have successfully reconstructed input da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.04227v1-abstract-full').style.display = 'inline'; document.getElementById('2406.04227v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.04227v1-abstract-full" style="display: none;"> In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent studies show that private training data can be leaked through many gradient attacks. While previous analytical-based attacks have successfully reconstructed input data from fully connected layers, their effectiveness diminishes when applied to convolutional layers. This paper introduces an advanced data leakage method to efficiently exploit convolutional layers' gradients. We present a surprising finding: even with non-fully invertible activation functions, such as ReLU, we can analytically reconstruct training samples from the gradients. To the best of our knowledge, this is the first analytical approach that successfully reconstructs convolutional layer inputs directly from the gradients, bypassing the need to reconstruct layers' outputs. Prior research has mainly concentrated on the weight constraints of convolution layers, overlooking the significance of gradient constraints. Our findings demonstrate that existing analytical methods used to estimate the risk of gradient attacks lack accuracy. In some layers, attacks can be launched with less than 5% of the reported constraints. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.04227v1-abstract-full').style.display = 'none'; document.getElementById('2406.04227v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Web Information Systems Engineering - WISE 2024. Lecture Notes in Computer Science, vol 15440 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.04102">arXiv:2406.04102</a> <span> [<a href="https://arxiv.org/pdf/2406.04102">pdf</a>, <a href="https://arxiv.org/format/2406.04102">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Geometry">cs.CG</span> </div> </div> <p class="title is-5 mathjax"> Chromatic Topological Data Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=di+Montesano%2C+S+C">Sebastiano Cultrera di Montesano</a>, <a href="/search/cs?searchtype=author&query=Draganov%2C+O">Ondrej Draganov</a>, <a href="/search/cs?searchtype=author&query=Edelsbrunner%2C+H">Herbert Edelsbrunner</a>, <a href="/search/cs?searchtype=author&query=Saghafian%2C+M">Morteza Saghafian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.04102v1-abstract-short" style="display: inline;"> Exploring the shape of point configurations has been a key driver in the evolution of TDA (short for topological data analysis) since its infancy. This survey illustrates the recent efforts to broaden these ideas to model spatial interactions among multiple configurations, each distinguished by a color. It describes advances in this area and prepares the ground for further exploration by mentionin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.04102v1-abstract-full').style.display = 'inline'; document.getElementById('2406.04102v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.04102v1-abstract-full" style="display: none;"> Exploring the shape of point configurations has been a key driver in the evolution of TDA (short for topological data analysis) since its infancy. This survey illustrates the recent efforts to broaden these ideas to model spatial interactions among multiple configurations, each distinguished by a color. It describes advances in this area and prepares the ground for further exploration by mentioning unresolved questions and promising research avenues while focusing on the overlap with discrete geometry. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.04102v1-abstract-full').style.display = 'none'; document.getElementById('2406.04102v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.17920">arXiv:2405.17920</a> <span> [<a href="https://arxiv.org/pdf/2405.17920">pdf</a>, <a href="https://arxiv.org/format/2405.17920">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> <p class="title is-5 mathjax"> Banana Trees for the Persistence in Time Series Experimentally </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ost%2C+L">Lara Ost</a>, <a href="/search/cs?searchtype=author&query=di+Montesano%2C+S+C">Sebastiano Cultrera di Montesano</a>, <a href="/search/cs?searchtype=author&query=Edelsbrunner%2C+H">Herbert Edelsbrunner</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="2405.17920v1-abstract-short" style="display: inline;"> In numerous fields, dynamic time series data require continuous updates, necessitating efficient data processing techniques for accurate analysis. This paper examines the banana tree data structure, specifically designed to efficiently maintain persistent homology -- a multi-scale topological descriptor -- for dynamically changing time series data. We implement this data structure and conduct an e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17920v1-abstract-full').style.display = 'inline'; document.getElementById('2405.17920v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.17920v1-abstract-full" style="display: none;"> In numerous fields, dynamic time series data require continuous updates, necessitating efficient data processing techniques for accurate analysis. This paper examines the banana tree data structure, specifically designed to efficiently maintain persistent homology -- a multi-scale topological descriptor -- for dynamically changing time series data. We implement this data structure and conduct an experimental study to assess its properties and runtime for update operations. Our findings indicate that banana trees are highly effective with unbiased random data, outperforming state-of-the-art static algorithms in these scenarios. Additionally, our results show that real-world time series share structural properties with unbiased random walks, suggesting potential practical utility for our implementation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17920v1-abstract-full').style.display = 'none'; document.getElementById('2405.17920v1-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 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/2405.15231">arXiv:2405.15231</a> <span> [<a href="https://arxiv.org/pdf/2405.15231">pdf</a>, <a href="https://arxiv.org/format/2405.15231">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"> Cardinality Estimation on Hyper-relational Knowledge Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Teng%2C+F">Fei Teng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haoyang Li</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Shimin Di</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Lei Chen</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="2405.15231v3-abstract-short" style="display: inline;"> Cardinality Estimation (CE) for query is to estimate the number of results without execution, which is an effective index in query optimization. Recently, CE for queries over knowlege graph (KGs) with triple facts has achieved great success. To more precisely represent facts, current researchers propose hyper-relational KGs (HKGs) to represent a triple fact with qualifiers providing additional con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15231v3-abstract-full').style.display = 'inline'; document.getElementById('2405.15231v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15231v3-abstract-full" style="display: none;"> Cardinality Estimation (CE) for query is to estimate the number of results without execution, which is an effective index in query optimization. Recently, CE for queries over knowlege graph (KGs) with triple facts has achieved great success. To more precisely represent facts, current researchers propose hyper-relational KGs (HKGs) to represent a triple fact with qualifiers providing additional context to the fact. However, existing CE methods, such as sampling and summary methods over KGs, perform unsatisfactorily on HKGs due to the complexity of qualifiers. Learning-based CE methods do not utilize qualifier information to learn query representation accurately, leading to poor performance. Also, there is only one limited CE benchmark for HKG query, which is not comprehensive and only covers limited patterns. The lack of querysets over HKG also becomes a bottleneck to comprehensively investigate CE problems on HKGs. In this work, we first construct diverse and unbiased hyper-relational querysets over three popular HKGs for investigating CE. Besides, we also propose a novel qualifier-aware graph neural network (GNN) model that effectively incorporates qualifier information and adaptively combines outputs from multiple GNN layers, to accurately predict the cardinality. Our experiments demonstrate that our model outperforms all state-of-the-art CE methods over three benchmarks on popular HKGs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15231v3-abstract-full').style.display = 'none'; document.getElementById('2405.15231v3-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 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/2405.09541">arXiv:2405.09541</a> <span> [<a href="https://arxiv.org/pdf/2405.09541">pdf</a>, <a href="https://arxiv.org/format/2405.09541">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Probability">math.PR</span> </div> </div> <p class="title is-5 mathjax"> Spectral complexity of deep neural networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Di+Lillo%2C+S">Simmaco Di Lillo</a>, <a href="/search/cs?searchtype=author&query=Marinucci%2C+D">Domenico Marinucci</a>, <a href="/search/cs?searchtype=author&query=Salvi%2C+M">Michele Salvi</a>, <a href="/search/cs?searchtype=author&query=Vigogna%2C+S">Stefano Vigogna</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="2405.09541v3-abstract-short" style="display: inline;"> It is well-known that randomly initialized, push-forward, fully-connected neural networks weakly converge to isotropic Gaussian processes, in the limit where the width of all layers goes to infinity. In this paper, we propose to use the angular power spectrum of the limiting field to characterize the complexity of the network architecture. In particular, we define sequences of random variables ass… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09541v3-abstract-full').style.display = 'inline'; document.getElementById('2405.09541v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.09541v3-abstract-full" style="display: none;"> It is well-known that randomly initialized, push-forward, fully-connected neural networks weakly converge to isotropic Gaussian processes, in the limit where the width of all layers goes to infinity. In this paper, we propose to use the angular power spectrum of the limiting field to characterize the complexity of the network architecture. In particular, we define sequences of random variables associated with the angular power spectrum, and provide a full characterization of the network complexity in terms of the asymptotic distribution of these sequences as the depth diverges. On this basis, we classify neural networks as low-disorder, sparse, or high-disorder; we show how this classification highlights a number of distinct features for standard activation functions, and in particular, sparsity properties of ReLU networks. Our theoretical results are also validated by numerical simulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09541v3-abstract-full').style.display = 'none'; document.getElementById('2405.09541v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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">MSC Class:</span> 68T07; 60G60; 33C55; 62M15 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.08122">arXiv:2405.08122</a> <span> [<a href="https://arxiv.org/pdf/2405.08122">pdf</a>, <a href="https://arxiv.org/format/2405.08122">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="Systems and Control">eess.SY</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/TCST.2024.3400571">10.1109/TCST.2024.3400571 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Equivariant Deep Learning of Mixed-Integer Optimal Control Solutions for Vehicle Decision Making and Motion Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reiter%2C+R">Rudolf Reiter</a>, <a href="/search/cs?searchtype=author&query=Quirynen%2C+R">Rien Quirynen</a>, <a href="/search/cs?searchtype=author&query=Diehl%2C+M">Moritz Diehl</a>, <a href="/search/cs?searchtype=author&query=Di+Cairano%2C+S">Stefano Di Cairano</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="2405.08122v1-abstract-short" style="display: inline;"> Mixed-integer quadratic programs (MIQPs) are a versatile way of formulating vehicle decision making and motion planning problems, where the prediction model is a hybrid dynamical system that involves both discrete and continuous decision variables. However, even the most advanced MIQP solvers can hardly account for the challenging requirements of automotive embedded platforms. Thus, we use machine… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.08122v1-abstract-full').style.display = 'inline'; document.getElementById('2405.08122v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.08122v1-abstract-full" style="display: none;"> Mixed-integer quadratic programs (MIQPs) are a versatile way of formulating vehicle decision making and motion planning problems, where the prediction model is a hybrid dynamical system that involves both discrete and continuous decision variables. However, even the most advanced MIQP solvers can hardly account for the challenging requirements of automotive embedded platforms. Thus, we use machine learning to simplify and hence speed up optimization. Our work builds on recent ideas for solving MIQPs in real-time by training a neural network to predict the optimal values of integer variables and solving the remaining problem by online quadratic programming. Specifically, we propose a recurrent permutation equivariant deep set that is particularly suited for imitating MIQPs that involve many obstacles, which is often the major source of computational burden in motion planning problems. Our framework comprises also a feasibility projector that corrects infeasible predictions of integer variables and considerably increases the likelihood of computing a collision-free trajectory. We evaluate the performance, safety and real-time feasibility of decision-making for autonomous driving using the proposed approach on realistic multi-lane traffic scenarios with interactive agents in SUMO simulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.08122v1-abstract-full').style.display = 'none'; document.getElementById('2405.08122v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 May, 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/2405.06290">arXiv:2405.06290</a> <span>  </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="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Path Planning and Motion Control for Accurate Positioning of Car-like Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dai%2C+J">Jin Dai</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zejiang Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yebin Wang</a>, <a href="/search/cs?searchtype=author&query=Quirynen%2C+R">Rien Quirynen</a>, <a href="/search/cs?searchtype=author&query=Di+Cairano%2C+S">Stefano Di Cairano</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="2405.06290v2-abstract-short" style="display: inline;"> This paper investigates the planning and control for accurate positioning of car-like robots. We propose a solution that integrates two modules: a motion planner, facilitated by the rapidly-exploring random tree algorithm and continuous-curvature (CC) steering technique, generates a CC trajectory as a reference; and a nonlinear model predictive controller (NMPC) regulates the robot to accurately t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06290v2-abstract-full').style.display = 'inline'; document.getElementById('2405.06290v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.06290v2-abstract-full" style="display: none;"> This paper investigates the planning and control for accurate positioning of car-like robots. We propose a solution that integrates two modules: a motion planner, facilitated by the rapidly-exploring random tree algorithm and continuous-curvature (CC) steering technique, generates a CC trajectory as a reference; and a nonlinear model predictive controller (NMPC) regulates the robot to accurately track the reference trajectory. Based on the $渭$-tangency conditions in prior art, we derive explicit existence conditions and develop associated computation methods for a special class of CC paths which not only admit the same driving patterns as Reeds-Shepp paths but also consist of cusp-free clothoid turns. Afterwards, we create an autonomous vehicle parking scenario where the NMPC endeavors to follow the reference trajectory. Feasibility and computational efficiency of the CC steering are validated by numerical simulation. CarSim-Simulink joint simulations statistically verify that with exactly same NMPC, the closed-loop system with CC trajectories as references substantially outperforms the case where Reeds-Shepp trajectories are used as references. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06290v2-abstract-full').style.display = 'none'; document.getElementById('2405.06290v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 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">The paper needs further revision to guarantee technical correctness and conciseness</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.02520">arXiv:2405.02520</a> <span> [<a href="https://arxiv.org/pdf/2405.02520">pdf</a>, <a href="https://arxiv.org/format/2405.02520">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> TurboFFT: A High-Performance Fast Fourier Transform with Fault Tolerance on GPU </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+S">Shixun Wu</a>, <a href="/search/cs?searchtype=author&query=Zhai%2C+Y">Yujia Zhai</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Jian%2C+Z">Zizhe Jian</a>, <a href="/search/cs?searchtype=author&query=Dai%2C+H">Huangliang Dai</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zizhong Chen</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</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="2405.02520v1-abstract-short" style="display: inline;"> The Fast Fourier Transform (FFT), as a core computation in a wide range of scientific applications, is increasingly threatened by reliability issues. In this paper, we introduce TurboFFT, a high-performance FFT implementation equipped with a two-sided checksum scheme that detects and corrects silent data corruptions at computing units efficiently. The proposed two-sided checksum addresses the erro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02520v1-abstract-full').style.display = 'inline'; document.getElementById('2405.02520v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.02520v1-abstract-full" style="display: none;"> The Fast Fourier Transform (FFT), as a core computation in a wide range of scientific applications, is increasingly threatened by reliability issues. In this paper, we introduce TurboFFT, a high-performance FFT implementation equipped with a two-sided checksum scheme that detects and corrects silent data corruptions at computing units efficiently. The proposed two-sided checksum addresses the error propagation issue by encoding a batch of input signals with different linear combinations, which not only allows fast batched error detection but also enables error correction on-the-fly instead of recomputing. We explore two-sided checksum designs at the kernel, thread, and threadblock levels, and provide a baseline FFT implementation competitive to the state-of-the-art, closed-source cuFFT. We demonstrate a kernel fusion strategy to mitigate and overlap the computation/memory overhead introduced by fault tolerance with underlying FFT computation. We present a template-based code generation strategy to reduce development costs and support a wide range of input sizes and data types. Experimental results on an NVIDIA A100 server GPU and a Tesla Turing T4 GPU demonstrate TurboFFT offers a competitive or superior performance compared to the closed-source library cuFFT. TurboFFT only incurs a minimum overhead (7\% to 15\% on average) compared to cuFFT, even under hundreds of error injections per minute for both single and double precision. TurboFFT achieves a 23\% improvement compared to existing fault tolerance FFT schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02520v1-abstract-full').style.display = 'none'; document.getElementById('2405.02520v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 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/2404.11015">arXiv:2404.11015</a> <span> [<a href="https://arxiv.org/pdf/2404.11015">pdf</a>, <a href="https://arxiv.org/format/2404.11015">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> FedFa: A Fully Asynchronous Training Paradigm for Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+H">Haotian Xu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaorui Zhang</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Benben Liu</a>, <a href="/search/cs?searchtype=author&query=Alharthi%2C+K+A">Khalid Ayed Alharthi</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+J">Jiannong Cao</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="2404.11015v2-abstract-short" style="display: inline;"> Federated learning has been identified as an efficient decentralized training paradigm for scaling the machine learning model training on a large number of devices while guaranteeing the data privacy of the trainers. FedAvg has become a foundational parameter update strategy for federated learning, which has been promising to eliminate the effect of the heterogeneous data across clients and guaran… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11015v2-abstract-full').style.display = 'inline'; document.getElementById('2404.11015v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.11015v2-abstract-full" style="display: none;"> Federated learning has been identified as an efficient decentralized training paradigm for scaling the machine learning model training on a large number of devices while guaranteeing the data privacy of the trainers. FedAvg has become a foundational parameter update strategy for federated learning, which has been promising to eliminate the effect of the heterogeneous data across clients and guarantee convergence. However, the synchronization parameter update barriers for each communication round during the training significant time on waiting, slowing down the training procedure. Therefore, recent state-of-the-art solutions propose using semi-asynchronous approaches to mitigate the waiting time cost with guaranteed convergence. Nevertheless, emerging semi-asynchronous approaches are unable to eliminate the waiting time completely. We propose a full asynchronous training paradigm, called FedFa, which can guarantee model convergence and eliminate the waiting time completely for federated learning by using a few buffered results on the server for parameter updating. Further, we provide theoretical proof of the convergence rate for our proposed FedFa. Extensive experimental results indicate our approach effectively improves the training performance of federated learning by up to 6x and 4x speedup compared to the state-of-the-art synchronous and semi-asynchronous strategies while retaining high accuracy in both IID and Non-IID scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11015v2-abstract-full').style.display = 'none'; document.getElementById('2404.11015v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IJCAI 2024: the 33rd International Joint Conference on Artificial Intelligence </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.03714">arXiv:2404.03714</a> <span> [<a href="https://arxiv.org/pdf/2404.03714">pdf</a>, <a href="https://arxiv.org/format/2404.03714">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </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/10.3390/electronics13091744">10.3390/electronics13091744 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> SpikeExplorer: hardware-oriented Design Space Exploration for Spiking Neural Networks on FPGA </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Padovano%2C+D">Dario Padovano</a>, <a href="/search/cs?searchtype=author&query=Carpegna%2C+A">Alessio Carpegna</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</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="2404.03714v1-abstract-short" style="display: inline;"> One of today's main concerns is to bring Artificial Intelligence power to embedded systems for edge applications. The hardware resources and power consumption required by state-of-the-art models are incompatible with the constrained environments observed in edge systems, such as IoT nodes and wearable devices. Spiking Neural Networks (SNNs) can represent a solution in this sense: inspired by neuro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03714v1-abstract-full').style.display = 'inline'; document.getElementById('2404.03714v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.03714v1-abstract-full" style="display: none;"> One of today's main concerns is to bring Artificial Intelligence power to embedded systems for edge applications. The hardware resources and power consumption required by state-of-the-art models are incompatible with the constrained environments observed in edge systems, such as IoT nodes and wearable devices. Spiking Neural Networks (SNNs) can represent a solution in this sense: inspired by neuroscience, they reach unparalleled power and resource efficiency when run on dedicated hardware accelerators. However, when designing such accelerators, the amount of choices that can be taken is huge. This paper presents SpikExplorer, a modular and flexible Python tool for hardware-oriented Automatic Design Space Exploration to automate the configuration of FPGA accelerators for SNNs. Using Bayesian optimizations, SpikerExplorer enables hardware-centric multi-objective optimization, supporting factors such as accuracy, area, latency, power, and various combinations during the exploration process. The tool searches the optimal network architecture, neuron model, and internal and training parameters, trying to reach the desired constraints imposed by the user. It allows for a straightforward network configuration, providing the full set of explored points for the user to pick the trade-off that best fits the needs. The potential of SpikExplorer is showcased using three benchmark datasets. It reaches 95.8% accuracy on the MNIST dataset, with a power consumption of 180mW/image and a latency of 0.12 ms/image, making it a powerful tool for automatically optimizing SNNs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03714v1-abstract-full').style.display = 'none'; document.getElementById('2404.03714v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.02840">arXiv:2404.02840</a> <span> [<a href="https://arxiv.org/pdf/2404.02840">pdf</a>, <a href="https://arxiv.org/ps/2404.02840">ps</a>, <a href="https://arxiv.org/format/2404.02840">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A Survey on Error-Bounded Lossy Compression for Scientific Datasets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jinyang Liu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kai Zhao</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+X">Xin Liang</a>, <a href="/search/cs?searchtype=author&query=Underwood%2C+R">Robert Underwood</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhaorui Zhang</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M">Milan Shah</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yafan Huang</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiajun Huang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xiaodong Yu</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+C">Congrong Ren</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hanqi Guo</a>, <a href="/search/cs?searchtype=author&query=Wilkins%2C+G">Grant Wilkins</a>, <a href="/search/cs?searchtype=author&query=Tao%2C+D">Dingwen Tao</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+J">Jiannan Tian</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+S">Sian Jin</a>, <a href="/search/cs?searchtype=author&query=Jian%2C+Z">Zizhe Jian</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Daoce Wang</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+H">MD Hasanur Rahman</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+B">Boyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Song%2C+S">Shihui Song</a>, <a href="/search/cs?searchtype=author&query=Calhoun%2C+J+C">Jon C. Calhoun</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Guanpeng Li</a>, <a href="/search/cs?searchtype=author&query=Yoshii%2C+K">Kazutomo Yoshii</a>, <a href="/search/cs?searchtype=author&query=Alharthi%2C+K+A">Khalid Ayed Alharthi</a> , et al. (1 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.02840v2-abstract-short" style="display: inline;"> Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving the reconstructed data fidelity very well. Many error-bounded lossy compressors have been developed for a wide range of parallel and distributed use cases for years. They are designed with distinct compression models and principles, such that each of them features particul… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02840v2-abstract-full').style.display = 'inline'; document.getElementById('2404.02840v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.02840v2-abstract-full" style="display: none;"> Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving the reconstructed data fidelity very well. Many error-bounded lossy compressors have been developed for a wide range of parallel and distributed use cases for years. They are designed with distinct compression models and principles, such that each of them features particular pros and cons. In this paper we provide a comprehensive survey of emerging error-bounded lossy compression techniques. The key contribution is fourfold. (1) We summarize a novel taxonomy of lossy compression into 6 classic models. (2) We provide a comprehensive survey of 10 commonly used compression components/modules. (3) We summarized pros and cons of 46 state-of-the-art lossy compressors and present how state-of-the-art compressors are designed based on different compression techniques. (4) We discuss how customized compressors are designed for specific scientific applications and use-cases. We believe this survey is useful to multiple communities including scientific applications, high-performance computing, lossy compression, and big data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02840v2-abstract-full').style.display = 'none'; document.getElementById('2404.02840v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 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">This paper has been submitted to ACM Computing journal. This is a revised version based on review comments</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.02826">arXiv:2404.02826</a> <span> [<a href="https://arxiv.org/pdf/2404.02826">pdf</a>, <a href="https://arxiv.org/ps/2404.02826">ps</a>, <a href="https://arxiv.org/format/2404.02826">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Methods for Astrophysics">astro-ph.IM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> An Error-Bounded Lossy Compression Method with Bit-Adaptive Quantization for Particle Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ren%2C+C">Congrong Ren</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Longtao Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+K">Kai Zhao</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hanqi Guo</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="2404.02826v2-abstract-short" style="display: inline;"> This paper presents error-bounded lossy compression tailored for particle datasets from diverse scientific applications in cosmology, fluid dynamics, and fusion energy sciences. As today's high-performance computing capabilities advance, these datasets often reach trillions of points, posing significant visualization, analysis, and storage challenges. While error-bounded lossy compression makes it… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02826v2-abstract-full').style.display = 'inline'; document.getElementById('2404.02826v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.02826v2-abstract-full" style="display: none;"> This paper presents error-bounded lossy compression tailored for particle datasets from diverse scientific applications in cosmology, fluid dynamics, and fusion energy sciences. As today's high-performance computing capabilities advance, these datasets often reach trillions of points, posing significant visualization, analysis, and storage challenges. While error-bounded lossy compression makes it possible to represent floating-point values with strict pointwise accuracy guarantees, the lack of correlations in particle data's storage ordering often limits the compression ratio. Inspired by quantization-encoding schemes in SZ lossy compressors, we dynamically determine the number of bits to encode particles of the dataset to increase the compression ratio. Specifically, we utilize a k-d tree to partition particles into subregions and generate ``bit boxes'' centered at particles for each subregion to encode their positions. These bit boxes ensure error control while reducing the bit count used for compression. We comprehensively evaluate our method against state-of-the-art compressors on cosmology, fluid dynamics, and fusion plasma datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02826v2-abstract-full').style.display = 'none'; document.getElementById('2404.02826v2-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">v1</span> submitted 3 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/2404.02163">arXiv:2404.02163</a> <span> [<a href="https://arxiv.org/pdf/2404.02163">pdf</a>, <a href="https://arxiv.org/format/2404.02163">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> FastqZip: An Improved Reference-Based Genome Sequence Lossy Compression Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yuanjian Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+H">Huihao Luo</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Zhijun Han</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yao Hu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yehui Yang</a>, <a href="/search/cs?searchtype=author&query=Chard%2C+K">Kyle Chard</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Foster%2C+I">Ian Foster</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiesheng Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.02163v1-abstract-short" style="display: inline;"> Storing and archiving data produced by next-generation sequencing (NGS) is a huge burden for research institutions. Reference-based compression algorithms are effective in dealing with these data. Our work focuses on compressing FASTQ format files with an improved reference-based compression algorithm to achieve a higher compression ratio than other state-of-the-art algorithms. We propose FastqZip… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02163v1-abstract-full').style.display = 'inline'; document.getElementById('2404.02163v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.02163v1-abstract-full" style="display: none;"> Storing and archiving data produced by next-generation sequencing (NGS) is a huge burden for research institutions. Reference-based compression algorithms are effective in dealing with these data. Our work focuses on compressing FASTQ format files with an improved reference-based compression algorithm to achieve a higher compression ratio than other state-of-the-art algorithms. We propose FastqZip, which uses a new method mapping the sequence to reference for compression, allows reads-reordering and lossy quality scores, and the BSC or ZPAQ algorithm to perform final lossless compression for a higher compression ratio and relatively fast speed. Our method ensures the sequence can be losslessly reconstructed while allowing lossless or lossy compression for the quality scores. We reordered the reads to get a higher compression ratio. We evaluate our algorithms on five datasets and show that FastqZip can outperform the SOTA algorithm Genozip by around 10% in terms of compression ratio while having an acceptable slowdown. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.02163v1-abstract-full').style.display = 'none'; document.getElementById('2404.02163v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 February, 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/2404.00383">arXiv:2404.00383</a> <span> [<a href="https://arxiv.org/pdf/2404.00383">pdf</a>, <a href="https://arxiv.org/format/2404.00383">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </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/IOLTS60994.2024.10616060">10.1109/IOLTS60994.2024.10616060 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> SpikingJET: Enhancing Fault Injection for Fully and Convolutional Spiking Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gogebakan%2C+A+B">Anil Bayram Gogebakan</a>, <a href="/search/cs?searchtype=author&query=Magliano%2C+E">Enrico Magliano</a>, <a href="/search/cs?searchtype=author&query=Carpegna%2C+A">Alessio Carpegna</a>, <a href="/search/cs?searchtype=author&query=Ruospo%2C+A">Annachiara Ruospo</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessandro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</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="2404.00383v1-abstract-short" style="display: inline;"> As artificial neural networks become increasingly integrated into safety-critical systems such as autonomous vehicles, devices for medical diagnosis, and industrial automation, ensuring their reliability in the face of random hardware faults becomes paramount. This paper introduces SpikingJET, a novel fault injector designed specifically for fully connected and convolutional Spiking Neural Network… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00383v1-abstract-full').style.display = 'inline'; document.getElementById('2404.00383v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.00383v1-abstract-full" style="display: none;"> As artificial neural networks become increasingly integrated into safety-critical systems such as autonomous vehicles, devices for medical diagnosis, and industrial automation, ensuring their reliability in the face of random hardware faults becomes paramount. This paper introduces SpikingJET, a novel fault injector designed specifically for fully connected and convolutional Spiking Neural Networks (SNNs). Our work underscores the critical need to evaluate the resilience of SNNs to hardware faults, considering their growing prominence in real-world applications. SpikingJET provides a comprehensive platform for assessing the resilience of SNNs by inducing errors and injecting faults into critical components such as synaptic weights, neuron model parameters, internal states, and activation functions. This paper demonstrates the effectiveness of Spiking-JET through extensive software-level experiments on various SNN architectures, revealing insights into their vulnerability and resilience to hardware faults. Moreover, highlighting the importance of fault resilience in SNNs contributes to the ongoing effort to enhance the reliability and safety of Neural Network (NN)-powered systems in diverse domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00383v1-abstract-full').style.display = 'none'; document.getElementById('2404.00383v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 March, 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">ACM Class:</span> I.2 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE 30th International Symposium on On-Line Testing and Robust System Design (IOLTS) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.17546">arXiv:2403.17546</a> <span> [<a href="https://arxiv.org/pdf/2403.17546">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="General Economics">econ.GN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> </div> <p class="title is-5 mathjax"> Decoding excellence: Mapping the demand for psychological traits of operations and supply chain professionals through text mining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Di+Luozzo%2C+S">S. Di Luozzo</a>, <a href="/search/cs?searchtype=author&query=Colladon%2C+A+F">A. Fronzetti Colladon</a>, <a href="/search/cs?searchtype=author&query=Schiraldi%2C+M+M">M. M. Schiraldi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.17546v1-abstract-short" style="display: inline;"> The current study proposes an innovative methodology for the profiling of psychological traits of Operations Management (OM) and Supply Chain Management (SCM) professionals. We use innovative methods and tools of text mining and social network analysis to map the demand for relevant skills from a set of job descriptions, with a focus on psychological characteristics. The proposed approach aims to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17546v1-abstract-full').style.display = 'inline'; document.getElementById('2403.17546v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.17546v1-abstract-full" style="display: none;"> The current study proposes an innovative methodology for the profiling of psychological traits of Operations Management (OM) and Supply Chain Management (SCM) professionals. We use innovative methods and tools of text mining and social network analysis to map the demand for relevant skills from a set of job descriptions, with a focus on psychological characteristics. The proposed approach aims to evaluate the market demand for specific traits by combining relevant psychological constructs, text mining techniques, and an innovative measure, namely, the Semantic Brand Score. We apply the proposed methodology to a dataset of job descriptions for OM and SCM professionals, with the objective of providing a mapping of their relevant required skills, including psychological characteristics. In addition, the analysis is then detailed by considering the region of the organization that issues the job description, its organizational size, and the seniority level of the open position in order to understand their nuances. Finally, topic modeling is used to examine key components and their relative significance in job descriptions. By employing a novel methodology and considering contextual factors, we provide an innovative understanding of the attitudinal traits that differentiate professionals. This research contributes to talent management, recruitment practices, and professional development initiatives, since it provides new figures and perspectives to improve the effectiveness and success of Operations Management and Supply Chain Management professionals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17546v1-abstract-full').style.display = 'none'; document.getElementById('2403.17546v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7; J.4; H.4.0 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.15953">arXiv:2403.15953</a> <span> [<a href="https://arxiv.org/pdf/2403.15953">pdf</a>, <a href="https://arxiv.org/format/2403.15953">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Understanding The Effectiveness of Lossy Compression in Machine Learning Training Sets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Underwood%2C+R">Robert Underwood</a>, <a href="/search/cs?searchtype=author&query=Calhoun%2C+J+C">Jon C. Calhoun</a>, <a href="/search/cs?searchtype=author&query=Di%2C+S">Sheng Di</a>, <a href="/search/cs?searchtype=author&query=Cappello%2C+F">Franck Cappello</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.15953v1-abstract-short" style="display: inline;"> Learning and Artificial Intelligence (ML/AI) techniques have become increasingly prevalent in high performance computing (HPC). However, these methods depend on vast volumes of floating point data for training and validation which need methods to share the data on a wide area network (WAN) or to transfer it from edge devices to data centers. Data compression can be a solution to these problems, bu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15953v1-abstract-full').style.display = 'inline'; document.getElementById('2403.15953v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.15953v1-abstract-full" style="display: none;"> Learning and Artificial Intelligence (ML/AI) techniques have become increasingly prevalent in high performance computing (HPC). However, these methods depend on vast volumes of floating point data for training and validation which need methods to share the data on a wide area network (WAN) or to transfer it from edge devices to data centers. Data compression can be a solution to these problems, but an in-depth understanding of how lossy compression affects model quality is needed. Prior work largely considers a single application or compression method. We designed a systematic methodology for evaluating data reduction techniques for ML/AI, and we use it to perform a very comprehensive evaluation with 17 data reduction methods on 7 ML/AI applications to show modern lossy compression methods can achieve a 50-100x compression ratio improvement for a 1% or less loss in quality. We identify critical insights that guide the future use and design of lossy compressors for ML/AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15953v1-abstract-full').style.display = 'none'; document.getElementById('2403.15953v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6; E.2; C.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.13730">arXiv:2403.13730</a> <span> [<a href="https://arxiv.org/pdf/2403.13730">pdf</a>, <a href="https://arxiv.org/format/2403.13730">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</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"> Projection-free computation of robust controllable sets with constrained zonotopes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vinod%2C+A+P">Abraham P. Vinod</a>, <a href="/search/cs?searchtype=author&query=Weiss%2C+A">Avishai Weiss</a>, <a href="/search/cs?searchtype=author&query=Di+Cairano%2C+S">Stefano Di Cairano</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.13730v2-abstract-short" style="display: inline;"> We study the problem of computing robust controllable sets for discrete-time linear systems with additive uncertainty. We propose a tractable and scalable approach to inner- and outer-approximate robust controllable sets using constrained zonotopes, when the additive uncertainty set is a symmetric, convex, and compact set. Our least-squares-based approach uses novel closed-form approximations of t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.13730v2-abstract-full').style.display = 'inline'; document.getElementById('2403.13730v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.13730v2-abstract-full" style="display: none;"> We study the problem of computing robust controllable sets for discrete-time linear systems with additive uncertainty. We propose a tractable and scalable approach to inner- and outer-approximate robust controllable sets using constrained zonotopes, when the additive uncertainty set is a symmetric, convex, and compact set. Our least-squares-based approach uses novel closed-form approximations of the Pontryagin difference between a constrained zonotopic minuend and a symmetric, convex, and compact subtrahend. Unlike existing approaches, our approach does not rely on convex optimization solvers, and is projection-free for ellipsoidal and zonotopic uncertainty sets. We also propose a least-squares-based approach to compute a convex, polyhedral outer-approximation to constrained zonotopes, and characterize sufficient conditions under which all these approximations are exact. We demonstrate the computational efficiency and scalability of our approach in several case studies, including the design of abort-safe rendezvous trajectories for a spacecraft in near-rectilinear halo orbit under uncertainty. Our approach can inner-approximate a 20-step robust controllable set for a 100-dimensional linear system in under 15 seconds on a standard computer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.13730v2-abstract-full').style.display = 'none'; document.getElementById('2403.13730v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">23 pages, 7 figures; Accepted for publication at Automatica. See https://youtu.be/6BPmHgxD3OI for the use of the proposed method in a simplified abort-safe rendezvous problem</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.10204">arXiv:2403.10204</a> <span> [<a href="https://arxiv.org/pdf/2403.10204">pdf</a>, <a href="https://arxiv.org/format/2403.10204">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Geometry">cs.CG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Combinatorics">math.CO</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/10.4230/LIPIcs.GD.2024.3">10.4230/LIPIcs.GD.2024.3 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> The Euclidean MST-ratio for Bi-colored Lattices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=di+Montesano%2C+S+C">Sebastiano Cultrera di Montesano</a>, <a href="/search/cs?searchtype=author&query=Draganov%2C+O">Ond艡ej Draganov</a>, <a href="/search/cs?searchtype=author&query=Edelsbrunner%2C+H">Herbert Edelsbrunner</a>, <a href="/search/cs?searchtype=author&query=Saghafian%2C+M">Morteza Saghafian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.10204v2-abstract-short" style="display: inline;"> Given a finite set, $A \subseteq \mathbb{R}^2$, and a subset, $B \subseteq A$, the \emph{MST-ratio} is the combined length of the minimum spanning trees of $B$ and $A \setminus B$ divided by the length of the minimum spanning tree of $A$. The question of the supremum, over all sets $A$, of the maximum, over all subsets $B$, is related to the Steiner ratio, and we prove this sup-max is between… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10204v2-abstract-full').style.display = 'inline'; document.getElementById('2403.10204v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.10204v2-abstract-full" style="display: none;"> Given a finite set, $A \subseteq \mathbb{R}^2$, and a subset, $B \subseteq A$, the \emph{MST-ratio} is the combined length of the minimum spanning trees of $B$ and $A \setminus B$ divided by the length of the minimum spanning tree of $A$. The question of the supremum, over all sets $A$, of the maximum, over all subsets $B$, is related to the Steiner ratio, and we prove this sup-max is between $2.154$ and $2.427$. Restricting ourselves to $2$-dimensional lattices, we prove that the sup-max is $2.0$, while the inf-max is $1.25$. By some margin the most difficult of these results is the upper bound for the inf-max, which we prove by showing that the hexagonal lattice cannot have MST-ratio larger than $1.25$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10204v2-abstract-full').style.display = 'none'; document.getElementById('2403.10204v2-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 15 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 52C05; 05C10 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> G.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.08397">arXiv:2401.08397</a> <span> [<a href="https://arxiv.org/pdf/2401.08397">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</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/LATS62223.2024.10534595">10.1109/LATS62223.2024.10534595 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Micro Architectural Events Aware Real-Time Embedded System Fault Injector </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Magliano%2C+E">Enrico Magliano</a>, <a href="/search/cs?searchtype=author&query=Carpegna%2C+A">Alessio Carpegna</a>, <a href="/search/cs?searchtype=author&query=Savino%2C+A">Alessadro Savino</a>, <a href="/search/cs?searchtype=author&query=Di+Carlo%2C+S">Stefano Di Carlo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.08397v2-abstract-short" style="display: inline;"> In contemporary times, the increasing complexity of the system poses significant challenges to the reliability, trustworthiness, and security of the SACRES. Key issues include the susceptibility to phenomena such as instantaneous voltage spikes, electromagnetic interference, neutron strikes, and out-of-range temperatures. These factors can induce switch state changes in transistors, resulting in b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08397v2-abstract-full').style.display = 'inline'; document.getElementById('2401.08397v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.08397v2-abstract-full" style="display: none;"> In contemporary times, the increasing complexity of the system poses significant challenges to the reliability, trustworthiness, and security of the SACRES. Key issues include the susceptibility to phenomena such as instantaneous voltage spikes, electromagnetic interference, neutron strikes, and out-of-range temperatures. These factors can induce switch state changes in transistors, resulting in bit-flipping, soft errors, and transient corruption of stored data in memory. The occurrence of soft errors, in turn, may lead to system faults that can propel the system into a hazardous state. Particularly in critical sectors like automotive, avionics, or aerospace, such malfunctions can have real-world implications, potentially causing harm to individuals. This paper introduces a novel fault injector designed to facilitate the monitoring, aggregation, and examination of micro-architectural events. This is achieved by harnessing the microprocessor's PMU and the debugging interface, specifically focusing on ensuring the repeatability of fault injections. The fault injection methodology targets bit-flipping within the memory system, affecting CPU registers and RAM. The outcomes of these fault injections enable a thorough analysis of the impact of soft errors and establish a robust correlation between the identified faults and the essential timing predictability demanded by SACRES. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08397v2-abstract-full').style.display = 'none'; document.getElementById('2401.08397v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE 25th Latin American Test Symposium (LATS) </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Di%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Di%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository