CINXE.COM

<html> <head>  <script async src="https://www.googletagmanager.com/gtag/js?id=UA-131826476-1"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'UA-131826476-1'); </script> <meta http-equiv="Content-type" content="text/html;charset=UTF-8">  <link rel="icon" href="/img/favicon.ico"> <link rel="icon" type="image/png" href="/img/favicon-16x16.png"> <link rel="icon" type="image/png" href="/img/favicon-32x32.png"> <title>Journal of Machine Learning Research</title> <link rel="alternate" type="application/rss+xml" href="/jmlr.xml" title="JMLR RSS"> <link rel="stylesheet" type="text/css" href="/style.css"> <style type="text/css"> . {font-family:verdana,helvetica,sans-serif} a {text-decoration:none;color:#3030a0} #fixed { position: absolute; top: 0; left: 0; width: 8em; height: 100%; } body > #fixed { position: fixed; } #content { margin-top: 1em; margin-left: 10em; margin-right: 0.5em; } img.jmlr { width: 7em; } img.rss { width: 2em; } ul li { margin-bottom: 0.5em; } </style> </head> <body> <div id="fixed"> <a align="right" href="/" target=_top><img align="right" class="jmlr" src="/img/jmlr.jpg" border="0"></a> <A href="/"> Home Page </A> <A href="/papers"> Papers </A> <A href="/author-info.html"> Submissions </A> <A href="/news.html"> News </A>  <A href="/editorial-board.html"> Editorial Board </A> <A href="/special_issues/"> Special Issues </A> <A href="/mloss">Open Source Software</A> <A href="https://proceedings.mlr.press/"> Proceedings (PMLR)</A> <A href="https://data.mlr.press/"> Data (DMLR) </A> <A href="/tmlr"> Transactions (TMLR) </A> <A href="/search-jmlr.html"> Search </A> <A href="/stats.html">Statistics</A> <A href="/manudb"> Login </A> <A href="/faq.html">Frequently Asked Questions </A> <A href="/contact.html"> Contact Us </A> <A href="/jmlr.xml"> <img src="/img/RSS.gif" class="rss" alt="RSS Feed"> </A> </div> <div id="content"> <h1>Journal of Machine Learning Research</h1> The Journal of Machine Learning Research (JMLR), <a href="/history.html">established in 2000</a>, provides an international forum for the electronic and paper publication of high-quality scholarly articles in all areas of machine learning. All published papers are freely available online. JMLR has a commitment to rigorous yet rapid reviewing. Final versions are <a href="papers"> published electronically</a> (ISSN 1533-7928) immediately upon receipt. Until the end of 2004, paper volumes (ISSN 1532-4435) were published 8 times annually and sold to libraries and individuals by the MIT Press. Paper volumes (ISSN 1532-4435) are now published and sold by <a href="http://www.mtome.com/">Microtome Publishing</a>. <h2>News</h2> <ul> <li>2024.02.18: <a href="/papers/v24">Volume 24</a> completed; <a href="/papers/v25">Volume 25</a> began. </li> <li>2023.01.20: <a href="/papers/v23">Volume 23</a> completed; <a href="/papers/v24">Volume 24</a> began. </li> <li>2022.07.20: New <a href="/special_issues/climate_change.html">special issue on climate change</a>.</li> <li>2022.02.18: New blog post: <a href="/news/2022/retrospectives.html">Retrospectives from 20 Years of JMLR </a>. </li> <li>2022.01.25: <a href="/papers/v22">Volume 22</a> completed; <a href="/papers/v23">Volume 23</a> began. </li> <li>2021.12.02: <a href="news/2021/schoelkopf-retirement.html">Message from outgoing co-EiC Bernhard Schölkopf</a>. </li> <li>2021.02.10: <a href="/papers/v21">Volume 21</a> completed; <a href="/papers/v22">Volume 22</a> began. </li> <li><a href="/news.html">More news ...</a></li> </ul> <h2>Latest papers</h2> <dl> <dt>Aequitas Flow: Streamlining Fair ML Experimentation</dt> <dd>Sérgio Jesus, Pedro Saleiro, Inês Oliveira e Silva, Beatriz M. Jorge, Rita P. Ribeiro, João Gama, Pedro Bizarro, Rayid Ghani, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/24-0677.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0677/24-0677.pdf'>pdf</a>][<a href="/papers/v25/24-0677.bib">bib</a>]      [<a href="https://github.com/dssg/aequitas">code</a>] </dl> <dl> <dt>Information Capacity Regret Bounds for Bandits with Mediator Feedback</dt> <dd>Khaled Eldowa, Nicolo Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli, 2024. [<a href='/papers/v25/24-0227.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0227/24-0227.pdf'>pdf</a>][<a href="/papers/v25/24-0227.bib">bib</a>] </dl> <dl> <dt>DAG-Informed Structure Learning from Multi-Dimensional Point Processes</dt> <dd>Chunming Zhang, Muhong Gao, Shengji Jia, 2024. [<a href='/papers/v25/24-0067.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0067/24-0067.pdf'>pdf</a>][<a href="/papers/v25/24-0067.bib">bib</a>] </dl> <dl> <dt>Optimizing Noise for f-Differential Privacy via Anti-Concentration and Stochastic Dominance</dt> <dd>Jordan Awan, Aishwarya Ramasethu, 2024. [<a href='/papers/v25/23-1624.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1624/23-1624.pdf'>pdf</a>][<a href="/papers/v25/23-1624.bib">bib</a>]      [<a href="https://github.com/JordanAwan/OptimizingNoiseForFDP">code</a>] </dl> <dl> <dt>A Rainbow in Deep Network Black Boxes</dt> <dd>Florentin Guth, Brice Ménard, Gaspar Rochette, Stéphane Mallat, 2024. [<a href='/papers/v25/23-1573.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1573/23-1573.pdf'>pdf</a>][<a href="/papers/v25/23-1573.bib">bib</a>]      [<a href="https://github.com/FlorentinGuth/Rainbow">code</a>] </dl> <dl> <dt>How Two-Layer Neural Networks Learn, One (Giant) Step at a Time</dt> <dd>Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan, 2024. [<a href='/papers/v25/23-1543.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1543/23-1543.pdf'>pdf</a>][<a href="/papers/v25/23-1543.bib">bib</a>] </dl> <dl> <dt>Hamiltonian Monte Carlo for efficient Gaussian sampling: long and random steps</dt> <dd>Simon Apers, Sander Gribling, Dániel Szilágyi, 2024. [<a href='/papers/v25/23-1521.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1521/23-1521.pdf'>pdf</a>][<a href="/papers/v25/23-1521.bib">bib</a>] </dl> <dl> <dt>Memorization With Neural Nets: Going Beyond the Worst Case</dt> <dd>Sjoerd Dirksen, Patrick Finke, Martin Genzel, 2024. [<a href='/papers/v25/23-1376.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1376/23-1376.pdf'>pdf</a>][<a href="/papers/v25/23-1376.bib">bib</a>]      [<a href="https://github.com/patrickfinke/memo">code</a>] </dl> <dl> <dt>PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates</dt> <dd>Zachary Frangella, Pratik Rathore, Shipu Zhao, Madeleine Udell, 2024. [<a href='/papers/v25/23-1187.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1187/23-1187.pdf'>pdf</a>][<a href="/papers/v25/23-1187.bib">bib</a>]      [<a href="https://github.com/udellgroup/PROMISE">code</a>] </dl> <dl> <dt>Causal effects of intervening variables in settings with unmeasured confounding</dt> <dd>Lan Wen, Aaron Sarvet, Mats Stensrud, 2024. [<a href='/papers/v25/23-1077.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1077/23-1077.pdf'>pdf</a>][<a href="/papers/v25/23-1077.bib">bib</a>] </dl> <dl> <dt>Lower Complexity Adaptation for Empirical Entropic Optimal Transport</dt> <dd>Michel Groppe, Shayan Hundrieser, 2024. [<a href='/papers/v25/23-0856.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0856/23-0856.pdf'>pdf</a>][<a href="/papers/v25/23-0856.bib">bib</a>]      [<a href="https://gitlab.gwdg.de/michel.groppe/eot-lca-simulations">code</a>] </dl> <dl> <dt>A Note on Entrywise Consistency for Mixed-data Matrix Completion</dt> <dd>Yunxiao Chen, Xiaoou Li, 2024. [<a href='/papers/v25/23-0834.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0834/23-0834.pdf'>pdf</a>][<a href="/papers/v25/23-0834.bib">bib</a>] </dl> <dl> <dt>A Characterization of Multioutput Learnability</dt> <dd>Vinod Raman, Unique Subedi, Ambuj Tewari, 2024. [<a href='/papers/v25/23-078.html'>abs</a>][<a target=_blank href='/papers/volume25/23-078/23-078.pdf'>pdf</a>][<a href="/papers/v25/23-078.bib">bib</a>] </dl> <dl> <dt>Sample Complexity of Variance-Reduced Distributionally Robust Q-Learning</dt> <dd>Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou, 2024. [<a href='/papers/v25/23-0526.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0526/23-0526.pdf'>pdf</a>][<a href="/papers/v25/23-0526.bib">bib</a>] </dl> <dl> <dt>Lower Bounds on the Bayesian Risk via Information Measures</dt> <dd>Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar, 2024. [<a href='/papers/v25/23-0361.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0361/23-0361.pdf'>pdf</a>][<a href="/papers/v25/23-0361.bib">bib</a>] </dl> <dl> <dt>Bayesian Structural Learning with Parametric Marginals for Count Data: An Application to Microbiota Systems</dt> <dd>Veronica Vinciotti, Pariya Behrouzi, Reza Mohammadi, 2024. [<a href='/papers/v25/23-0056.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0056/23-0056.pdf'>pdf</a>][<a href="/papers/v25/23-0056.bib">bib</a>] </dl> <dl> <dt>Transfer Learning with Uncertainty Quantification: Random Effect Calibration of Source to Target (RECaST)</dt> <dd>Jimmy Hickey, Jonathan P. Williams, Emily C. Hector, 2024. [<a href='/papers/v25/22-1369.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1369/22-1369.pdf'>pdf</a>][<a href="/papers/v25/22-1369.bib">bib</a>]      [<a href="https://github.com/JimmyJHickey/RECaST">code</a>] </dl> <dl> <dt>Inference on High-dimensional Single-index Models with Streaming Data</dt> <dd>Dongxiao Han, Jinhan Xie, Jin Liu, Liuquan Sun, Jian Huang, Bei Jiang, Linglong Kong, 2024. [<a href='/papers/v25/22-1124.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1124/22-1124.pdf'>pdf</a>][<a href="/papers/v25/22-1124.bib">bib</a>] </dl> <dl> <dt>On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport</dt> <dd>Minhui Huang, Shiqian Ma, Lifeng Lai, 2024. [<a href='/papers/v25/22-0524.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0524/22-0524.pdf'>pdf</a>][<a href="/papers/v25/22-0524.bib">bib</a>] </dl> <dl> <dt>ENNS: Variable Selection, Regression, Classification, and Deep Neural Network for High-Dimensional Data</dt> <dd>Kaixu Yang, Arkaprabha Ganguli, Tapabrata Maiti, 2024. [<a href='/papers/v25/21-0893.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0893/21-0893.pdf'>pdf</a>][<a href="/papers/v25/21-0893.bib">bib</a>] </dl> <dl> <dt>On the Optimality of Gaussian Kernel Based Nonparametric Tests against Smooth Alternatives</dt> <dd>Tong Li, Ming Yuan, 2024. [<a href='/papers/v25/20-1228.html'>abs</a>][<a target=_blank href='/papers/volume25/20-1228/20-1228.pdf'>pdf</a>][<a href="/papers/v25/20-1228.bib">bib</a>] </dl> <dl> <dt>Open-Source Conversational AI with SpeechBrain 1.0</dt> <dd>Mirco Ravanelli, Titouan Parcollet, Adel Moumen, Sylvain de Langen, Cem Subakan, Peter Plantinga, Yingzhi Wang, Pooneh Mousavi, Luca Della Libera, Artem Ploujnikov, Francesco Paissan, Davide Borra, Salah Zaiem, Zeyu Zhao, Shucong Zhang, Georgios Karakasidis, Sung-Lin Yeh, Pierre Champion, Aku Rouhe, Rudolf Braun, Florian Mai, Juan Zuluaga-Gomez, Seyed Mahed Mousavi, Andreas Nautsch, Ha Nguyen, Xuechen Liu, Sangeet Sagar, Jarod Duret, Salima Mdhaffar, Gaëlle Laperrière, Mickael Rouvier, Renato De Mori, Yannick Estève, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/24-0991.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0991/24-0991.pdf'>pdf</a>][<a href="/papers/v25/24-0991.bib">bib</a>]      [<a href="https://speechbrain.github.io/">code</a>] </dl> <dl> <dt>Triple Component Matrix Factorization: Untangling Global, Local, and Noisy Components</dt> <dd>Naichen Shi, Salar Fattahi, Raed Al Kontar, 2024. [<a href='/papers/v25/24-0400.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0400/24-0400.pdf'>pdf</a>][<a href="/papers/v25/24-0400.bib">bib</a>]      [<a href="https://github.com/UMDataScienceLab/TCMF">code</a>] </dl> <dl> <dt>Generalization on the Unseen, Logic Reasoning and Degree Curriculum</dt> <dd>Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk, 2024. [<a href='/papers/v25/24-0220.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0220/24-0220.pdf'>pdf</a>][<a href="/papers/v25/24-0220.bib">bib</a>]      [<a href="https://github.com/aryol/GOTU">code</a>] </dl> <dl> <dt>Goal-Space Planning with Subgoal Models</dt> <dd>Chunlok Lo, Kevin Roice, Parham Mohammad Panahi, Scott M. Jordan, Adam White, Gabor Mihucz, Farzane Aminmansour, Martha White, 2024. [<a href='/papers/v25/24-0040.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0040/24-0040.pdf'>pdf</a>][<a href="/papers/v25/24-0040.bib">bib</a>] </dl> <dl> <dt>Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Constrained Optimization</dt> <dd>Enming Liang, Minghua Chen, Steven H. Low, 2024. [<a href='/papers/v25/23-1577.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1577/23-1577.pdf'>pdf</a>][<a href="/papers/v25/23-1577.bib">bib</a>]      [<a href="https://github.com/emliang/Homeomorphic-Projection">code</a>] </dl> <dl> <dt>Label Noise Robustness of Conformal Prediction</dt> <dd>Bat-Sheva Einbinder, Shai Feldman, Stephen Bates, Anastasios N. Angelopoulos, Asaf Gendler, Yaniv Romano, 2024. [<a href='/papers/v25/23-1549.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1549/23-1549.pdf'>pdf</a>][<a href="/papers/v25/23-1549.bib">bib</a>] </dl> <dl> <dt>PAPAL: A Provable PArticle-based Primal-Dual ALgorithm for Mixed Nash Equilibrium</dt> <dd>Shihong Ding, Hanze Dong, Cong Fang, Zhouchen Lin, Tong Zhang, 2024. [<a href='/papers/v25/23-1522.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1522/23-1522.pdf'>pdf</a>][<a href="/papers/v25/23-1522.bib">bib</a>] </dl> <dl> <dt>Geometric Learning with Positively Decomposable Kernels</dt> <dd>Nathael Da Costa, Cyrus Mostajeran, Juan-Pablo Ortega, Salem Said, 2024. [<a href='/papers/v25/23-1400.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1400/23-1400.pdf'>pdf</a>][<a href="/papers/v25/23-1400.bib">bib</a>] </dl> <dl> <dt>Mentored Learning: Improving Generalization and Convergence of Student Learner</dt> <dd>Xiaofeng Cao, Yaming Guo, Heng Tao Shen, Ivor W. Tsang, James T. Kwok, 2024. [<a href='/papers/v25/23-1213.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1213/23-1213.pdf'>pdf</a>][<a href="/papers/v25/23-1213.bib">bib</a>] </dl> <dl> <dt>Robust Principal Component Analysis using Density Power Divergence</dt> <dd>Subhrajyoty Roy, Ayanendranath Basu, Abhik Ghosh, 2024. [<a href='/papers/v25/23-1096.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1096/23-1096.pdf'>pdf</a>][<a href="/papers/v25/23-1096.bib">bib</a>] </dl> <dl> <dt>Graphical Dirichlet Process for Clustering Non-Exchangeable Grouped Data</dt> <dd>Arhit Chakrabarti, Yang Ni, Ellen Ruth A. Morris, Michael L. Salinas, Robert S. Chapkin, Bani K. Mallick, 2024. [<a href='/papers/v25/23-1048.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1048/23-1048.pdf'>pdf</a>][<a href="/papers/v25/23-1048.bib">bib</a>]      [<a href="https://github.com/Arhit-Chakrabarti/GDPSamp">code</a>] </dl> <dl> <dt>Stability and L2-penalty in Model Averaging</dt> <dd>Hengkun Zhu, Guohua Zou, 2024. [<a href='/papers/v25/23-0853.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0853/23-0853.pdf'>pdf</a>][<a href="/papers/v25/23-0853.bib">bib</a>] </dl> <dl> <dt>Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK</dt> <dd>Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Yingbin Liang, Zhangyang Wang, 2024. [<a href='/papers/v25/23-0831.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0831/23-0831.pdf'>pdf</a>][<a href="/papers/v25/23-0831.bib">bib</a>] </dl> <dl> <dt>Optimal Weighted Random Forests</dt> <dd>Xinyu Chen, Dalei Yu, Xinyu Zhang, 2024. [<a href='/papers/v25/23-0607.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0607/23-0607.pdf'>pdf</a>][<a href="/papers/v25/23-0607.bib">bib</a>]      [<a href="https://github.com/XinyuChen-hey/Optimal-Weighted-Random-Forests">code</a>] </dl> <dl> <dt>Efficient Active Manifold Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization</dt> <dd>Hao Wang, Ye Wang, Xiangyu Yang, 2024. [<a href='/papers/v25/23-0449.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0449/23-0449.pdf'>pdf</a>][<a href="/papers/v25/23-0449.bib">bib</a>] </dl> <dl> <dt>Empirical Design in Reinforcement Learning</dt> <dd>Andrew Patterson, Samuel Neumann, Martha White, Adam White, 2024. [<a href='/papers/v25/23-0183.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0183/23-0183.pdf'>pdf</a>][<a href="/papers/v25/23-0183.bib">bib</a>] </dl> <dl> <dt>A Data-Adaptive RKHS Prior for Bayesian Learning of Kernels in Operators</dt> <dd>Neil K. Chada, Quanjun Lang, Fei Lu, Xiong Wang, 2024. [<a href='/papers/v25/22-1491.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1491/22-1491.pdf'>pdf</a>][<a href="/papers/v25/22-1491.bib">bib</a>] </dl> <dl> <dt>GGD: Grafting Gradient Descent</dt> <dd>Yanjing Feng, Yongdao Zhou, 2024. [<a href='/papers/v25/22-1236.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1236/22-1236.pdf'>pdf</a>][<a href="/papers/v25/22-1236.bib">bib</a>]      [<a href="https://github.com/oo0mmmm/GGD">code</a>] </dl> <dl> <dt>Debiasing Evaluations That Are Biased by Evaluations</dt> <dd>Jingyan Wang, Ivan Stelmakh, Yuting Wei, Nihar Shah, 2024. [<a href='/papers/v25/22-0775.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0775/22-0775.pdf'>pdf</a>][<a href="/papers/v25/22-0775.bib">bib</a>]      [<a href="https://github.com/jingyanw/outcome-induced-debiasing">code</a>] </dl> <dl> <dt>Optimal Learning Policies for Differential Privacy in Multi-armed Bandits</dt> <dd>Siwei Wang, Jun Zhu, 2024. [<a href='/papers/v25/21-1267.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1267/21-1267.pdf'>pdf</a>][<a href="/papers/v25/21-1267.bib">bib</a>] </dl> <dl> <dt>Data-Efficient Policy Evaluation Through Behavior Policy Search</dt> <dd>Josiah P. Hanna, Yash Chandak, Philip S. Thomas, Martha White, Peter Stone, Scott Niekum, 2024. [<a href='/papers/v25/21-0346.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0346/21-0346.pdf'>pdf</a>][<a href="/papers/v25/21-0346.bib">bib</a>] </dl> <dl> <dt>Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence</dt> <dd>Ashwin Pananjady, Vidya Muthukumar, Andrew Thangaraj, 2024. [<a href='/papers/v25/24-0511.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0511/24-0511.pdf'>pdf</a>][<a href="/papers/v25/24-0511.bib">bib</a>]      [<a href="https://github.com/andrewthan/Missing-Mass">code</a>] </dl> <dl> <dt>Estimating the Replication Probability of Significant Classification Benchmark Experiments</dt> <dd>Daniel Berrar, 2024. [<a href='/papers/v25/24-0158.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0158/24-0158.pdf'>pdf</a>][<a href="/papers/v25/24-0158.bib">bib</a>] </dl> <dl> <dt>Causal Discovery with Generalized Linear Models through Peeling Algorithms</dt> <dd>Minjie Wang, Xiaotong Shen, Wei Pan, 2024. [<a href='/papers/v25/23-1228.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1228/23-1228.pdf'>pdf</a>][<a href="/papers/v25/23-1228.bib">bib</a>]      [<a href="https://github.com/minjie-wang/GAMPI">code</a>] </dl> <dl> <dt>Spectral Regularized Kernel Goodness-of-Fit Tests</dt> <dd>Omar Hagrass, Bharath K. Sriperumbudur, Bing Li, 2024. [<a href='/papers/v25/23-1031.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1031/23-1031.pdf'>pdf</a>][<a href="/papers/v25/23-1031.bib">bib</a>] </dl> <dl> <dt>Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality</dt> <dd>François G. Ged, Maria Han Veiga, 2024. [<a href='/papers/v25/23-0879.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0879/23-0879.pdf'>pdf</a>][<a href="/papers/v25/23-0879.bib">bib</a>] </dl> <dl> <dt>Non-Euclidean Monotone Operator Theory and Applications</dt> <dd>Alexander Davydov, Saber Jafarpour, Anton V. Proskurnikov, Francesco Bullo, 2024. [<a href='/papers/v25/23-0805.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0805/23-0805.pdf'>pdf</a>][<a href="/papers/v25/23-0805.bib">bib</a>] </dl> <dl> <dt>Stochastic Regularized Majorization-Minimization with weakly convex and multi-convex surrogates</dt> <dd>Hanbaek Lyu, 2024. [<a href='/papers/v25/23-0349.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0349/23-0349.pdf'>pdf</a>][<a href="/papers/v25/23-0349.bib">bib</a>]      [<a href="https://github.com/HanbaekLyu/SRMM">code</a>] </dl> <dl> <dt>Pure Differential Privacy for Functional Summaries with a Laplace-like Process</dt> <dd>Haotian Lin, Matthew Reimherr, 2024. [<a href='/papers/v25/22-1384.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1384/22-1384.pdf'>pdf</a>][<a href="/papers/v25/22-1384.bib">bib</a>] </dl> <dl> <dt>Sparse Recovery With Multiple Data Streams: An Adaptive Sequential Testing Approach</dt> <dd>Weinan Wang, Bowen Gang, Wenguang Sun, 2024. [<a href='/papers/v25/22-1310.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1310/22-1310.pdf'>pdf</a>][<a href="/papers/v25/22-1310.bib">bib</a>] </dl> <dl> <dt>Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning</dt> <dd>Luofeng Liao, Zuyue Fu, Zhuoran Yang, Yixin Wang, Dingli Ma, Mladen Kolar, Zhaoran Wang, 2024. [<a href='/papers/v25/22-0965.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0965/22-0965.pdf'>pdf</a>][<a href="/papers/v25/22-0965.bib">bib</a>] </dl> <dl> <dt>Identifying Causal Eﬀects using Instrumental Time Series: Nuisance IV and Correcting for the Past</dt> <dd>Nikolaj Thams, Rikke Søndergaard, Sebastian Weichwald, Jonas Peters, 2024. [<a href='/papers/v25/22-0262.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0262/22-0262.pdf'>pdf</a>][<a href="/papers/v25/22-0262.bib">bib</a>]      [<a href="https://github.com/nikolajthams/its-time/">code</a>] </dl> <dl> <dt>RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control</dt> <dd>Jonas Eschmann, Dario Albani, Giuseppe Loianno, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/24-0248.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0248/24-0248.pdf'>pdf</a>][<a href="/papers/v25/24-0248.bib">bib</a>]      [<a href="https://github.com/rl-tools/rl-tools">code</a>] </dl> <dl> <dt>White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?</dt> <dd>Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Hao Bai, Yuexiang Zhai, Benjamin D. Haeffele, Yi Ma, 2024. [<a href='/papers/v25/23-1547.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1547/23-1547.pdf'>pdf</a>][<a href="/papers/v25/23-1547.bib">bib</a>]      [<a href="https://ma-lab-berkeley.github.io/CRATE">code</a>] </dl> <dl> <dt>Commutative Scaling of Width and Depth in Deep Neural Networks</dt> <dd>Soufiane Hayou, 2024. [<a href='/papers/v25/23-1163.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1163/23-1163.pdf'>pdf</a>][<a href="/papers/v25/23-1163.bib">bib</a>] </dl> <dl> <dt>Value-Distributional Model-Based Reinforcement Learning</dt> <dd>Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters, 2024. [<a href='/papers/v25/23-0913.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0913/23-0913.pdf'>pdf</a>][<a href="/papers/v25/23-0913.bib">bib</a>]      [<a href="https://github.com/boschresearch/dist-mbrl">code</a>] </dl> <dl> <dt>Optimistic Search: Change Point Estimation for Large-scale Data via Adaptive Logarithmic Queries</dt> <dd>Solt Kovács, Housen Li, Lorenz Haubner, Axel Munk, Peter Bühlmann, 2024. [<a href='/papers/v25/23-0871.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0871/23-0871.pdf'>pdf</a>][<a href="/papers/v25/23-0871.bib">bib</a>] </dl> <dl> <dt>PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization</dt> <dd>Qiqi Duan, Guochen Zhou, Chang Shao, Zhuowei Wang, Mingyang Feng, Yuwei Huang, Yajing Tan, Yijun Yang, Qi Zhao, Yuhui Shi, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0386.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0386/23-0386.pdf'>pdf</a>][<a href="/papers/v25/23-0386.bib">bib</a>]      [<a href="https://github.com/Evolutionary-Intelligence/pypop">code</a>] </dl> <dl> <dt>Evidence Estimation in Gaussian Graphical Models Using a Telescoping Block Decomposition of the Precision Matrix</dt> <dd>Anindya Bhadra, Ksheera Sagar, David Rowe, Sayantan Banerjee, Jyotishka Datta, 2024. [<a href='/papers/v25/23-0254.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0254/23-0254.pdf'>pdf</a>][<a href="/papers/v25/23-0254.bib">bib</a>]      [<a href="https://github.com/dp-rho/graphicalEvidence">code</a>] </dl> <dl> <dt>An Asymptotic Study of Discriminant and Vote-Averaging Schemes for Randomly-Projected Linear Discriminants</dt> <dd>Lama B. Niyazi, Abla Kammoun, Hayssam Dahrouj, Mohamed-Slim Alouini, Tareq Y. Al-Naffouri, 2024. [<a href='/papers/v25/22-1367.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1367/22-1367.pdf'>pdf</a>][<a href="/papers/v25/22-1367.bib">bib</a>]      [<a href="https://github.com/niyazil/DA-RP-ensemble_tuning">code</a>] </dl> <dl> <dt>Learning and scoring Gaussian latent variable causal models with unknown additive interventions</dt> <dd>Armeen Taeb, Juan L. Gamella, Christina Heinze-Deml, Peter Bühlmann, 2024. [<a href='/papers/v25/22-0979.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0979/22-0979.pdf'>pdf</a>][<a href="/papers/v25/22-0979.bib">bib</a>]      [<a href="https://github.com/juangamella/ut-lvce-paper">code</a>] </dl> <dl> <dt>Non-splitting Neyman-Pearson Classifiers</dt> <dd>Jingming Wang, Lucy Xia, Zhigang Bao, Xin Tong, 2024. [<a href='/papers/v25/22-0795.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0795/22-0795.pdf'>pdf</a>][<a href="/papers/v25/22-0795.bib">bib</a>] </dl> <dl> <dt>Studying the Interplay between Information Loss and Operation Loss in Representations for Classification</dt> <dd>Jorge F. Silva, Felipe Tobar, Mario Vicuña, Felipe Cordova, 2024. [<a href='/papers/v25/21-1551.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1551/21-1551.pdf'>pdf</a>][<a href="/papers/v25/21-1551.bib">bib</a>] </dl> <dl> <dt>skscope: Fast Sparsity-Constrained Optimization in Python</dt> <dd>Zezhi Wang, Junxian Zhu, Xueqin Wang, Jin Zhu, Huiyang Pen, Peng Chen, Anran Wang, Xiaoke Zhang, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-1574.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1574/23-1574.pdf'>pdf</a>][<a href="/papers/v25/23-1574.bib">bib</a>]      [<a href="https://github.com/abess-team/skscope">code</a>] </dl> <dl> <dt>aeon: a Python Toolkit for Learning from Time Series</dt> <dd>Matthew Middlehurst, Ali Ismail-Fawaz, Antoine Guillaume, Christopher Holder, David Guijo-Rubio, Guzal Bulatova, Leonidas Tsaprounis, Lukasz Mentel, Martin Walter, Patrick Schäfer, Anthony Bagnall, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-1444.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1444/23-1444.pdf'>pdf</a>][<a href="/papers/v25/23-1444.bib">bib</a>]      [<a href="https://github.com/aeon-toolkit/aeon">code</a>] </dl> <dl> <dt>Compressed and distributed least-squares regression: convergence rates with applications to federated learning</dt> <dd>Constantin Philippenko, Aymeric Dieuleveut, 2024. [<a href='/papers/v25/23-1040.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1040/23-1040.pdf'>pdf</a>][<a href="/papers/v25/23-1040.bib">bib</a>]      [<a href="https://github.com/philipco/structured_noise">code</a>] </dl> <dl> <dt>Contamination-source based K-sample clustering</dt> <dd>Xavier Milhaud, Denys Pommeret, Yahia Salhi, Pierre Vandekerkhove, 2024. [<a href='/papers/v25/23-0914.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0914/23-0914.pdf'>pdf</a>][<a href="/papers/v25/23-0914.bib">bib</a>] </dl> <dl> <dt>Measuring Sample Quality in Algorithms for Intractable Normalizing Function Problems</dt> <dd>Bokgyeong Kang, John Hughes, Murali Haran, 2024. [<a href='/papers/v25/23-0810.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0810/23-0810.pdf'>pdf</a>][<a href="/papers/v25/23-0810.bib">bib</a>]      [<a href="https://github.com/bokgyeong/Diagnostics">code</a>] </dl> <dl> <dt>OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research</dt> <dd>Jiaming Ji, Jiayi Zhou, Borong Zhang, Juntao Dai, Xuehai Pan, Ruiyang Sun, Weidong Huang, Yiran Geng, Mickel Liu, Yaodong Yang, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0681.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0681/23-0681.pdf'>pdf</a>][<a href="/papers/v25/23-0681.bib">bib</a>]      [<a href="https://github.com/PKU-Alignment/omnisafe">code</a>] </dl> <dl> <dt>Random Smoothing Regularization in Kernel Gradient Descent Learning</dt> <dd>Liang Ding, Tianyang Hu, Jiahang Jiang, Donghao Li, Wenjia Wang, Yuan Yao, 2024. [<a href='/papers/v25/23-0580.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0580/23-0580.pdf'>pdf</a>][<a href="/papers/v25/23-0580.bib">bib</a>] </dl> <dl> <dt>MLRegTest: A Benchmark for the Machine Learning of Regular Languages</dt> <dd>Sam van der Poel, Dakotah Lambert, Kalina Kostyszyn, Tiantian Gao, Rahul Verma, Derek Andersen, Joanne Chau, Emily Peterson, Cody St. Clair, Paul Fodor, Chihiro Shibata, Jeffrey Heinz, 2024. [<a href='/papers/v25/23-0518.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0518/23-0518.pdf'>pdf</a>][<a href="/papers/v25/23-0518.bib">bib</a>]      [<a href="https://doi.org/10.5061/dryad.dncjsxm4h">code</a>] </dl> <dl> <dt>A tensor factorization model of multilayer network interdependence</dt> <dd>Izabel Aguiar, Dane Taylor, Johan Ugander, 2024. [<a href='/papers/v25/23-0205.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0205/23-0205.pdf'>pdf</a>][<a href="/papers/v25/23-0205.bib">bib</a>]      [<a href="https://github.com/izabelaguiar/NNTuck">code</a>] </dl> <dl> <dt>Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces</dt> <dd>Iskander Azangulov, Andrei Smolensky, Alexander Terenin, Viacheslav Borovitskiy, 2024. [<a href='/papers/v25/23-0115.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0115/23-0115.pdf'>pdf</a>][<a href="/papers/v25/23-0115.bib">bib</a>]      [<a href="https://github.com/imbirik/LieStationaryKernels">code</a>] </dl> <dl> <dt>Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case</dt> <dd>Iskander Azangulov, Andrei Smolensky, Alexander Terenin, Viacheslav Borovitskiy, 2024. [<a href='/papers/v25/22-1434.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1434/22-1434.pdf'>pdf</a>][<a href="/papers/v25/22-1434.bib">bib</a>]      [<a href="https://github.com/imbirik/LieStationaryKernels">code</a>] </dl> <dl> <dt>On Doubly Robust Inference for Double Machine Learning in Semiparametric Regression</dt> <dd>Oliver Dukes, Stijn Vansteelandt, David Whitney, 2024. [<a href='/papers/v25/22-1233.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1233/22-1233.pdf'>pdf</a>][<a href="/papers/v25/22-1233.bib">bib</a>]      [<a href="https://github.com/ordukes/DRInference/tree/main">code</a>] </dl> <dl> <dt>Deep Neural Network Approximation of Invariant Functions through Dynamical Systems</dt> <dd>Qianxiao Li, Ting Lin, Zuowei Shen, 2024. [<a href='/papers/v25/22-0982.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0982/22-0982.pdf'>pdf</a>][<a href="/papers/v25/22-0982.bib">bib</a>] </dl> <dl> <dt>A Statistical Experimental Design Method for Constructing Deterministic Sensing Matrices for Compressed Sensing</dt> <dd>Youran Qi, Xu He, Tzu-Hsiang Hung, Peter Chien, 2024. [<a href='/papers/v25/22-0760.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0760/22-0760.pdf'>pdf</a>][<a href="/papers/v25/22-0760.bib">bib</a>] </dl> <dl> <dt>Functional optimal transport: regularized map estimation and domain adaptation for functional data</dt> <dd>Jiacheng Zhu, Aritra Guha, Dat Do, Mengdi Xu, XuanLong Nguyen, Ding Zhao, 2024. [<a href='/papers/v25/22-0217.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0217/22-0217.pdf'>pdf</a>][<a href="/papers/v25/22-0217.bib">bib</a>]      [<a href="https://github.com/Jiacheng-Zhu-AIML/FOT">code</a>] </dl> <dl> <dt>Desiderata for Representation Learning: A Causal Perspective</dt> <dd>Yixin Wang, Michael I. Jordan, 2024. [<a href='/papers/v25/21-107.html'>abs</a>][<a target=_blank href='/papers/volume25/21-107/21-107.pdf'>pdf</a>][<a href="/papers/v25/21-107.bib">bib</a>]      [<a href="https://github.com/yixinwang/representation-causal-public">code</a>] </dl> <dl> <dt>Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization</dt> <dd>Huan Li, Zhouchen Lin, 2024. [<a href='/papers/v25/21-0475.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0475/21-0475.pdf'>pdf</a>][<a href="/papers/v25/21-0475.bib">bib</a>] </dl> <dl> <dt>Pearl: A Production-Ready Reinforcement Learning Agent</dt> <dd>Zheqing Zhu, Rodrigo de Salvo Braz, Jalaj Bhandari, Daniel Jiang, Yi Wan, Yonathan Efroni, Liyuan Wang, Ruiyang Xu, Hongbo Guo, Alex Nikulkov, Dmytro Korenkevych, Urun Dogan, Frank Cheng, Zheng Wu, Wanqiao Xu, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/24-0196.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0196/24-0196.pdf'>pdf</a>][<a href="/papers/v25/24-0196.bib">bib</a>]      [<a href="http://github.com/facebookresearch/pearl">code</a>] </dl> <dl> <dt>Boundary constrained Gaussian processes for robust physics-informed machine learning of linear partial differential equations</dt> <dd>David Dalton, Alan Lazarus, Hao Gao, Dirk Husmeier, 2024. [<a href='/papers/v25/23-1508.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1508/23-1508.pdf'>pdf</a>][<a href="/papers/v25/23-1508.bib">bib</a>]      [<a href="https://github.com/dodaltuin/jax-pigp/tree/main/examples/BCGPs">code</a>] </dl> <dl> <dt>Almost Sure Convergence Rates Analysis and Saddle Avoidance of Stochastic Gradient Methods</dt> <dd>Jun Liu, Ye Yuan, 2024. [<a href='/papers/v25/23-1436.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1436/23-1436.pdf'>pdf</a>][<a href="/papers/v25/23-1436.bib">bib</a>] </dl> <dl> <dt>False discovery proportion envelopes with m-consistency</dt> <dd>Meah Iqraa, Blanchard Gilles, Roquain Etienne, 2024. [<a href='/papers/v25/23-1025.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1025/23-1025.pdf'>pdf</a>][<a href="/papers/v25/23-1025.bib">bib</a>] </dl> <dl> <dt>Wasserstein Proximal Coordinate Gradient Algorithms</dt> <dd>Rentian Yao, Xiaohui Chen, Yun Yang, 2024. [<a href='/papers/v25/23-0889.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0889/23-0889.pdf'>pdf</a>][<a href="/papers/v25/23-0889.bib">bib</a>] </dl> <dl> <dt>Concentration and Moment Inequalities for General Functions of Independent Random Variables with Heavy Tails</dt> <dd>Shaojie Li, Yong Liu, 2024. [<a href='/papers/v25/23-0744.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0744/23-0744.pdf'>pdf</a>][<a href="/papers/v25/23-0744.bib">bib</a>] </dl> <dl> <dt>Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies</dt> <dd>Boris Hanin, 2024. [<a href='/papers/v25/23-0643.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0643/23-0643.pdf'>pdf</a>][<a href="/papers/v25/23-0643.bib">bib</a>] </dl> <dl> <dt>On Regularized Radon-Nikodym Differentiation</dt> <dd>Duc Hoan Nguyen, Werner Zellinger, Sergei Pereverzyev, 2024. [<a href='/papers/v25/23-0567.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0567/23-0567.pdf'>pdf</a>][<a href="/papers/v25/23-0567.bib">bib</a>] </dl> <dl> <dt>pgmpy: A Python Toolkit for Bayesian Networks</dt> <dd>Ankur Ankan, Johannes Textor, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0487.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0487/23-0487.pdf'>pdf</a>][<a href="/papers/v25/23-0487.bib">bib</a>]      [<a href="https://github.com/pgmpy">code</a>] </dl> <dl> <dt>Recursive Estimation of Conditional Kernel Mean Embeddings</dt> <dd>Ambrus Tamás, Balázs Csanád Csáji, 2024. [<a href='/papers/v25/23-0168.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0168/23-0168.pdf'>pdf</a>][<a href="/papers/v25/23-0168.bib">bib</a>] </dl> <dl> <dt>Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling</dt> <dd>Mert Gurbuzbalaban, Yuanhan Hu, Lingjiong Zhu, 2024. [<a href='/papers/v25/22-1443.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1443/22-1443.pdf'>pdf</a>][<a href="/papers/v25/22-1443.bib">bib</a>] </dl> <dl> <dt>Fast Rates in Pool-Based Batch Active Learning</dt> <dd>Claudio Gentile, Zhilei Wang, Tong Zhang, 2024. [<a href='/papers/v25/22-1409.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1409/22-1409.pdf'>pdf</a>][<a href="/papers/v25/22-1409.bib">bib</a>] </dl> <dl> <dt>On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis for Parametric Models</dt> <dd>Xuetong Wu, Mingming Gong, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu, 2024. [<a href='/papers/v25/22-1024.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1024/22-1024.pdf'>pdf</a>][<a href="/papers/v25/22-1024.bib">bib</a>] </dl> <dl> <dt>Mean-Field Approximation of Cooperative Constrained Multi-Agent Reinforcement Learning (CMARL)</dt> <dd>Washim Uddin Mondal, Vaneet Aggarwal, Satish V. Ukkusuri, 2024. [<a href='/papers/v25/22-0956.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0956/22-0956.pdf'>pdf</a>][<a href="/papers/v25/22-0956.bib">bib</a>] </dl> <dl> <dt>Structured Optimal Variational Inference for Dynamic Latent Space Models</dt> <dd>Peng Zhao, Anirban Bhattacharya, Debdeep Pati, Bani K. Mallick, 2024. [<a href='/papers/v25/22-0514.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0514/22-0514.pdf'>pdf</a>][<a href="/papers/v25/22-0514.bib">bib</a>]      [<a href="https://github.com/pengzhaostat/SMF-structured-variational-inference">code</a>] </dl> <dl> <dt>Stable and Consistent Density-Based Clustering via Multiparameter Persistence</dt> <dd>Alexander Rolle, Luis Scoccola, 2024. [<a href='/papers/v25/21-1185.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1185/21-1185.pdf'>pdf</a>][<a href="/papers/v25/21-1185.bib">bib</a>]      [<a href="https://github.com/LuisScoccola/persistable">code</a>] </dl> <dl> <dt>Faster Randomized Methods for Orthogonality Constrained Problems</dt> <dd>Boris Shustin, Haim Avron, 2024. [<a href='/papers/v25/21-1022.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1022/21-1022.pdf'>pdf</a>][<a href="/papers/v25/21-1022.bib">bib</a>] </dl> <dl> <dt>Estimation of Sparse Gaussian Graphical Models with Hidden Clustering Structure</dt> <dd>Meixia Lin, Defeng Sun, Kim-Chuan Toh, Chengjing Wang, 2024. [<a href='/papers/v25/20-354.html'>abs</a>][<a target=_blank href='/papers/volume25/20-354/20-354.pdf'>pdf</a>][<a href="/papers/v25/20-354.bib">bib</a>] </dl> <dl> <dt>Rethinking Discount Regularization: New Interpretations, Unintended Consequences, and Solutions for Regularization in Reinforcement Learning</dt> <dd>Sarah Rathnam, Sonali Parbhoo, Siddharth Swaroop, Weiwei Pan, Susan A. Murphy, Finale Doshi-Velez, 2024. [<a href='/papers/v25/24-0087.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0087/24-0087.pdf'>pdf</a>][<a href="/papers/v25/24-0087.bib">bib</a>]      [<a href="https://github.com/dtak/rethinking_discount_reg_public">code</a>] </dl> <dl> <dt>PromptBench: A Unified Library for Evaluation of Large Language Models</dt> <dd>Kaijie Zhu, Qinlin Zhao, Hao Chen, Jindong Wang, Xing Xie, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/24-0023.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0023/24-0023.pdf'>pdf</a>][<a href="/papers/v25/24-0023.bib">bib</a>]      [<a href="https://github.com/microsoft/promptbench">code</a>] </dl> <dl> <dt>Gaussian Interpolation Flows</dt> <dd>Yuan Gao, Jian Huang, and Yuling Jiao, 2024. [<a href='/papers/v25/23-1515.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1515/23-1515.pdf'>pdf</a>][<a href="/papers/v25/23-1515.bib">bib</a>] </dl> <dl> <dt>Gaussian Mixture Models with Rare Events</dt> <dd>Xuetong Li, Jing Zhou, Hansheng Wang, 2024. [<a href='/papers/v25/23-1245.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1245/23-1245.pdf'>pdf</a>][<a href="/papers/v25/23-1245.bib">bib</a>] </dl> <dl> <dt>On the Concentration of the Minimizers of Empirical Risks</dt> <dd>Paul Escande, 2024. [<a href='/papers/v25/23-1149.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1149/23-1149.pdf'>pdf</a>][<a href="/papers/v25/23-1149.bib">bib</a>] </dl> <dl> <dt>Variance estimation in graphs with the fused lasso</dt> <dd>Oscar Hernan Madrid Padilla, 2024. [<a href='/papers/v25/23-1061.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1061/23-1061.pdf'>pdf</a>][<a href="/papers/v25/23-1061.bib">bib</a>] </dl> <dl> <dt>Random measure priors in Bayesian recovery from sketches</dt> <dd>Mario Beraha, Stefano Favaro, Matteo Sesia, 2024. [<a href='/papers/v25/23-1058.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1058/23-1058.pdf'>pdf</a>][<a href="/papers/v25/23-1058.bib">bib</a>]      [<a href="https://github.com/mberaha/BNPSketching">code</a>] </dl> <dl> <dt>From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs</dt> <dd>Lorenz Richter, Leon Sallandt, Nikolas Nüsken, 2024. [<a href='/papers/v25/23-0982.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0982/23-0982.pdf'>pdf</a>][<a href="/papers/v25/23-0982.bib">bib</a>]      [<a href="https://github.com/lorenzrichter/PDE-backward-solver">code</a>] </dl> <dl> <dt>Label Alignment Regularization for Distribution Shift</dt> <dd>Ehsan Imani, Guojun Zhang, Runjia Li, Jun Luo, Pascal Poupart, Philip H.S. Torr, Yangchen Pan, 2024. [<a href='/papers/v25/23-0899.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0899/23-0899.pdf'>pdf</a>][<a href="/papers/v25/23-0899.bib">bib</a>]      [<a href="https://github.com/EhsanEI/lar/">code</a>] </dl> <dl> <dt>Fairness in Survival Analysis with Distributionally Robust Optimization</dt> <dd>Shu Hu, George H. Chen, 2024. [<a href='/papers/v25/23-0888.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0888/23-0888.pdf'>pdf</a>][<a href="/papers/v25/23-0888.bib">bib</a>]      [<a href="https://github.com/discovershu/DRO_survival">code</a>] </dl> <dl> <dt>FineMorphs: Affine-Diffeomorphic Sequences for Regression</dt> <dd>Michele Lohr, Laurent Younes, 2024. [<a href='/papers/v25/23-0824.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0824/23-0824.pdf'>pdf</a>][<a href="/papers/v25/23-0824.bib">bib</a>] </dl> <dl> <dt>Tensor-train methods for sequential state and parameter learning in state-space models</dt> <dd>Yiran Zhao, Tiangang Cui, 2024. [<a href='/papers/v25/23-0743.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0743/23-0743.pdf'>pdf</a>][<a href="/papers/v25/23-0743.bib">bib</a>]      [<a href="https://github.com/DeepTransport/tensor-ssm-paper-demo">code</a>] </dl> <dl> <dt>Memory of recurrent networks: Do we compute it right?</dt> <dd>Giovanni Ballarin, Lyudmila Grigoryeva, Juan-Pablo Ortega, 2024. [<a href='/papers/v25/23-0568.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0568/23-0568.pdf'>pdf</a>][<a href="/papers/v25/23-0568.bib">bib</a>]      [<a href="https://github.com/Learning-of-Dynamic-Processes/memorycapacity">code</a>] </dl> <dl> <dt>The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis</dt> <dd>El Mehdi Achour, François Malgouyres, Sébastien Gerchinovitz, 2024. [<a href='/papers/v25/23-0493.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0493/23-0493.pdf'>pdf</a>][<a href="/papers/v25/23-0493.bib">bib</a>] </dl> <dl> <dt>High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise</dt> <dd>Liam Madden, Emiliano Dall'Anese, Stephen Becker, 2024. [<a href='/papers/v25/23-0466.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0466/23-0466.pdf'>pdf</a>][<a href="/papers/v25/23-0466.bib">bib</a>]      [<a href="https://github.com/liammadden/sgd">code</a>] </dl> <dl> <dt>Euler Characteristic Tools for Topological Data Analysis</dt> <dd>Olympio Hacquard, Vadim Lebovici, 2024. [<a href='/papers/v25/23-0353.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0353/23-0353.pdf'>pdf</a>][<a href="/papers/v25/23-0353.bib">bib</a>]      [<a href="https://github.com/vadimlebovici/eulearning">code</a>] </dl> <dl> <dt>Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization</dt> <dd>Cameron Jakub, Mihai Nica, 2024. [<a href='/papers/v25/23-0350.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0350/23-0350.pdf'>pdf</a>][<a href="/papers/v25/23-0350.bib">bib</a>]      [<a href="https://github.com/camjakub/Depth-Degeneracy-in-Neural-Networks">code</a>] </dl> <dl> <dt>Fortuna: A Library for Uncertainty Quantification in Deep Learning</dt> <dd>Gianluca Detommaso, Alberto Gasparin, Michele Donini, Matthias Seeger, Andrew Gordon Wilson, Cedric Archambeau, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0145.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0145/23-0145.pdf'>pdf</a>][<a href="/papers/v25/23-0145.bib">bib</a>]      [<a href="https://github.com/awslabs/fortuna">code</a>] </dl> <dl> <dt>Characterization of translation invariant MMD on Rd and connections with Wasserstein distances</dt> <dd>Thibault Modeste, Clément Dombry, 2024. [<a href='/papers/v25/22-1338.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1338/22-1338.pdf'>pdf</a>][<a href="/papers/v25/22-1338.bib">bib</a>] </dl> <dl> <dt>On the Hyperparameters in Stochastic Gradient Descent with Momentum</dt> <dd>Bin Shi, 2024. [<a href='/papers/v25/22-1189.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1189/22-1189.pdf'>pdf</a>][<a href="/papers/v25/22-1189.bib">bib</a>] </dl> <dl> <dt>Improved Random Features for Dot Product Kernels</dt> <dd>Jonas Wacker, Motonobu Kanagawa, Maurizio Filippone, 2024. [<a href='/papers/v25/22-0118.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0118/22-0118.pdf'>pdf</a>][<a href="/papers/v25/22-0118.bib">bib</a>]      [<a href="https://github.com/joneswack/dp-rfs">code</a>] </dl> <dl> <dt>Regret Analysis of Bilateral Trade with a Smoothed Adversary</dt> <dd>Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi, 2024. [<a href='/papers/v25/23-1627.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1627/23-1627.pdf'>pdf</a>][<a href="/papers/v25/23-1627.bib">bib</a>] </dl> <dl> <dt>Invariant Physics-Informed Neural Networks for Ordinary Differential Equations</dt> <dd>Shivam Arora, Alex Bihlo, Francis Valiquette, 2024. [<a href='/papers/v25/23-1511.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1511/23-1511.pdf'>pdf</a>][<a href="/papers/v25/23-1511.bib">bib</a>] </dl> <dl> <dt>Distribution Learning via Neural Differential Equations: A Nonparametric Statistical Perspective</dt> <dd>Youssef Marzouk, Zhi (Robert) Ren, Sven Wang, Jakob Zech, 2024. [<a href='/papers/v25/23-1280.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1280/23-1280.pdf'>pdf</a>][<a href="/papers/v25/23-1280.bib">bib</a>] </dl> <dl> <dt>Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression</dt> <dd>Joseph Shenouda, Rahul Parhi, Kangwook Lee, Robert D. Nowak, 2024. [<a href='/papers/v25/23-0677.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0677/23-0677.pdf'>pdf</a>][<a href="/papers/v25/23-0677.bib">bib</a>] </dl> <dl> <dt>Individual-centered Partial Information in Social Networks</dt> <dd>Xiao Han, Y. X. Rachel Wang, Qing Yang, Xin Tong, 2024. [<a href='/papers/v25/23-0005.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0005/23-0005.pdf'>pdf</a>][<a href="/papers/v25/23-0005.bib">bib</a>] </dl> <dl> <dt>Data-driven Automated Negative Control Estimation (DANCE): Search for, Validation of, and Causal Inference with Negative Controls</dt> <dd>Erich Kummerfeld, Jaewon Lim, Xu Shi, 2024. [<a href='/papers/v25/22-1062.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1062/22-1062.pdf'>pdf</a>][<a href="/papers/v25/22-1062.bib">bib</a>]      [<a href="https://github.com/imjaewon07/DANCE">code</a>] </dl> <dl> <dt>Continuous Prediction with Experts' Advice</dt> <dd>Nicholas J. A. Harvey, Christopher Liaw, Victor S. Portella, 2024. [<a href='/papers/v25/22-0803.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0803/22-0803.pdf'>pdf</a>][<a href="/papers/v25/22-0803.bib">bib</a>] </dl> <dl> <dt>Memory-Efficient Sequential Pattern Mining with Hybrid Tries</dt> <dd>Amin Hosseininasab, Willem-Jan van Hoeve, Andre A. Cire, 2024. [<a href='/papers/v25/22-0125.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0125/22-0125.pdf'>pdf</a>][<a href="/papers/v25/22-0125.bib">bib</a>]      [<a href="https://github.com/aminhn/HTMiner">code</a>] </dl> <dl> <dt>Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds</dt> <dd>Zhenghao Xu, Xiang Ji, Minshuo Chen, Mengdi Wang, Tuo Zhao, 2024. [<a href='/papers/v25/24-0066.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0066/24-0066.pdf'>pdf</a>][<a href="/papers/v25/24-0066.bib">bib</a>] </dl> <dl> <dt>Split Conformal Prediction and Non-Exchangeable Data</dt> <dd>Roberto I. Oliveira, Paulo Orenstein, Thiago Ramos, João Vitor Romano, 2024. [<a href='/papers/v25/23-1553.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1553/23-1553.pdf'>pdf</a>][<a href="/papers/v25/23-1553.bib">bib</a>]      [<a href="https://github.com/jv-rv/split-conformal-nonexchangeable">code</a>] </dl> <dl> <dt>Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model</dt> <dd>Rashmi Ranjan Bhuyan, Adel Javanmard, Sungchul Kim, Gourab Mukherjee, Ryan A. Rossi, Tong Yu, Handong Zhao, 2024. [<a href='/papers/v25/23-1365.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1365/23-1365.pdf'>pdf</a>][<a href="/papers/v25/23-1365.bib">bib</a>] </dl> <dl> <dt>Sparse Graphical Linear Dynamical Systems</dt> <dd>Emilie Chouzenoux, Victor Elvira, 2024. [<a href='/papers/v25/23-0878.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0878/23-0878.pdf'>pdf</a>][<a href="/papers/v25/23-0878.bib">bib</a>] </dl> <dl> <dt>Statistical analysis for a penalized EM algorithm in high-dimensional mixture linear regression model</dt> <dd>Ning Wang, Xin Zhang, Qing Mai, 2024. [<a href='/papers/v25/23-0296.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0296/23-0296.pdf'>pdf</a>][<a href="/papers/v25/23-0296.bib">bib</a>] </dl> <dl> <dt>Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds</dt> <dd>Hao Liang, Zhi-Quan Luo, 2024. [<a href='/papers/v25/22-1253.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1253/22-1253.pdf'>pdf</a>][<a href="/papers/v25/22-1253.bib">bib</a>] </dl> <dl> <dt>Low-Rank Matrix Estimation in the Presence of Change-Points</dt> <dd>Lei Shi, Guanghui Wang, Changliang Zou, 2024. [<a href='/papers/v25/22-0852.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0852/22-0852.pdf'>pdf</a>][<a href="/papers/v25/22-0852.bib">bib</a>] </dl> <dl> <dt>A Framework for Improving the Reliability of Black-box Variational Inference</dt> <dd>Manushi Welandawe, Michael Riis Andersen, Aki Vehtari, Jonathan H. Huggins, 2024. [<a href='/papers/v25/22-0327.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0327/22-0327.pdf'>pdf</a>][<a href="/papers/v25/22-0327.bib">bib</a>]      [<a href="https://github.com/jhuggins/viabel">code</a>] </dl> <dl> <dt>Understanding Entropic Regularization in GANs</dt> <dd>Daria Reshetova, Yikun Bai, Xiugang Wu, Ayfer Özgür, 2024. [<a href='/papers/v25/21-1295.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1295/21-1295.pdf'>pdf</a>][<a href="/papers/v25/21-1295.bib">bib</a>] </dl> <dl> <dt>BenchMARL: Benchmarking Multi-Agent Reinforcement Learning</dt> <dd>Matteo Bettini, Amanda Prorok, Vincent Moens, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-1612.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1612/23-1612.pdf'>pdf</a>][<a href="/papers/v25/23-1612.bib">bib</a>]      [<a href="https://github.com/facebookresearch/BenchMARL">code</a>] </dl> <dl> <dt>Learning from many trajectories</dt> <dd>Stephen Tu, Roy Frostig, Mahdi Soltanolkotabi, 2024. [<a href='/papers/v25/23-1145.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1145/23-1145.pdf'>pdf</a>][<a href="/papers/v25/23-1145.bib">bib</a>] </dl> <dl> <dt>Interpretable algorithmic fairness in structured and unstructured data</dt> <dd>Hari Bandi, Dimitris Bertsimas, Thodoris Koukouvinos, Sofie Kupiec, 2024. [<a href='/papers/v25/23-0816.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0816/23-0816.pdf'>pdf</a>][<a href="/papers/v25/23-0816.bib">bib</a>] </dl> <dl> <dt>FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization</dt> <dd>José A. Carrillo, Nicolás García Trillos, Sixu Li, Yuhua Zhu, 2024. [<a href='/papers/v25/23-0764.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0764/23-0764.pdf'>pdf</a>][<a href="/papers/v25/23-0764.bib">bib</a>] </dl> <dl> <dt>On the Connection between Lp- and Risk Consistency and its Implications on Regularized Kernel Methods</dt> <dd>Hannes Köhler, 2024. [<a href='/papers/v25/23-0397.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0397/23-0397.pdf'>pdf</a>][<a href="/papers/v25/23-0397.bib">bib</a>] </dl> <dl> <dt>Pre-trained Gaussian Processes for Bayesian Optimization</dt> <dd>Zi Wang, George E. Dahl, Kevin Swersky, Chansoo Lee, Zachary Nado, Justin Gilmer, Jasper Snoek, Zoubin Ghahramani, 2024. [<a href='/papers/v25/23-0269.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0269/23-0269.pdf'>pdf</a>][<a href="/papers/v25/23-0269.bib">bib</a>]      [<a href="https://github.com/google-research/hyperbo/">code</a>] </dl> <dl> <dt>Heterogeneity-aware Clustered Distributed Learning for Multi-source Data Analysis</dt> <dd>Yuanxing Chen, Qingzhao Zhang, Shuangge Ma, Kuangnan Fang, 2024. [<a href='/papers/v25/23-0059.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0059/23-0059.pdf'>pdf</a>][<a href="/papers/v25/23-0059.bib">bib</a>] </dl> <dl> <dt>From Small Scales to Large Scales: Distance-to-Measure Density based Geometric Analysis of Complex Data</dt> <dd>Katharina Proksch, Christoph Alexander Weikamp, Thomas Staudt, Benoit Lelandais, Christophe Zimmer, 2024. [<a href='/papers/v25/22-1344.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1344/22-1344.pdf'>pdf</a>][<a href="/papers/v25/22-1344.bib">bib</a>]      [<a href="https://github.com/cweitkamp3/DTMdemo">code</a>] </dl> <dl> <dt>PAMI: An Open-Source Python Library for Pattern Mining</dt> <dd>Uday Kiran Rage, Veena Pamalla, Masashi Toyoda, Masaru Kitsuregawa, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/22-1026.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1026/22-1026.pdf'>pdf</a>][<a href="/papers/v25/22-1026.bib">bib</a>]      [<a href="https://github.com/UdayLab/PAMI">code</a>] </dl> <dl> <dt>Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case</dt> <dd>Arnaud Descours, Arnaud Guillin, Manon Michel, Boris Nectoux, 2024. [<a href='/papers/v25/22-0952.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0952/22-0952.pdf'>pdf</a>][<a href="/papers/v25/22-0952.bib">bib</a>] </dl> <dl> <dt>Risk Measures and Upper Probabilities: Coherence and Stratification</dt> <dd>Christian Fröhlich, Robert C. Williamson, 2024. [<a href='/papers/v25/22-0641.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0641/22-0641.pdf'>pdf</a>][<a href="/papers/v25/22-0641.bib">bib</a>] </dl> <dl> <dt>Parallel-in-Time Probabilistic Numerical ODE Solvers</dt> <dd>Nathanael Bosch, Adrien Corenflos, Fatemeh Yaghoobi, Filip Tronarp, Philipp Hennig, Simo Särkkä, 2024. [<a href='/papers/v25/23-1261.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1261/23-1261.pdf'>pdf</a>][<a href="/papers/v25/23-1261.bib">bib</a>]      [<a href="https://github.com/nathanaelbosch/parallel-in-time-ode-filters">code</a>] </dl> <dl> <dt>Scalable High-Dimensional Multivariate Linear Regression for Feature-Distributed Data</dt> <dd>Shuo-Chieh Huang, Ruey S. Tsay, 2024. [<a href='/papers/v25/23-0882.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0882/23-0882.pdf'>pdf</a>][<a href="/papers/v25/23-0882.bib">bib</a>] </dl> <dl> <dt>Dropout Regularization Versus l2-Penalization in the Linear Model</dt> <dd>Gabriel Clara, Sophie Langer, Johannes Schmidt-Hieber, 2024. [<a href='/papers/v25/23-0803.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0803/23-0803.pdf'>pdf</a>][<a href="/papers/v25/23-0803.bib">bib</a>] </dl> <dl> <dt>Efficient Convex Algorithms for Universal Kernel Learning</dt> <dd>Aleksandr Talitckii, Brendon Colbert, Matthew M. Peet, 2024. [<a href='/papers/v25/23-0528.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0528/23-0528.pdf'>pdf</a>][<a href="/papers/v25/23-0528.bib">bib</a>]      [<a href="https://github.com/CyberneticSCL/TKL-version-0.9">code</a>] </dl> <dl> <dt>Manifold Learning by Mixture Models of VAEs for Inverse Problems</dt> <dd>Giovanni S. Alberti, Johannes Hertrich, Matteo Santacesaria, Silvia Sciutto, 2024. [<a href='/papers/v25/23-0396.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0396/23-0396.pdf'>pdf</a>][<a href="/papers/v25/23-0396.bib">bib</a>]      [<a href="https://github.com/johertrich/Manifold_Mixture_VAEs">code</a>] </dl> <dl> <dt>An Algorithmic Framework for the Optimization of Deep Neural Networks Architectures and Hyperparameters</dt> <dd>Julie Keisler, El-Ghazali Talbi, Sandra Claudel, Gilles Cabriel, 2024. [<a href='/papers/v25/23-0166.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0166/23-0166.pdf'>pdf</a>][<a href="/papers/v25/23-0166.bib">bib</a>]      [<a href="https://github.com/JulieKeisler/DRAGON">code</a>] </dl> <dl> <dt>Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity</dt> <dd>Laixi Shi, Yuejie Chi, 2024. [<a href='/papers/v25/22-1482.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1482/22-1482.pdf'>pdf</a>][<a href="/papers/v25/22-1482.bib">bib</a>]      [<a href="https://github.com/Laixishi/Robust-RL-with-KL-divergence">code</a>] </dl> <dl> <dt>Grokking phase transitions in learning local rules with gradient descent</dt> <dd>Bojan Žunkovič, Enej Ilievski, 2024. [<a href='/papers/v25/22-1228.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1228/22-1228.pdf'>pdf</a>][<a href="/papers/v25/22-1228.bib">bib</a>]      [<a href="https://github.com/qml-tn/grokking">code</a>] </dl> <dl> <dt>Unsupervised Tree Boosting for Learning Probability Distributions</dt> <dd>Naoki Awaya, Li Ma, 2024. [<a href='/papers/v25/22-0980.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0980/22-0980.pdf'>pdf</a>][<a href="/papers/v25/22-0980.bib">bib</a>]      [<a href="https://github.com/MaStatLab/boostPM">code</a>] </dl> <dl> <dt>Linear Regression With Unmatched Data: A Deconvolution Perspective</dt> <dd>Mona Azadkia, Fadoua Balabdaoui, 2024. [<a href='/papers/v25/22-0930.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0930/22-0930.pdf'>pdf</a>][<a href="/papers/v25/22-0930.bib">bib</a>] </dl> <dl> <dt>Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit</dt> <dd>Karl Hajjar, Lénaïc Chizat, Christophe Giraud, 2024. [<a href='/papers/v25/21-1260.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1260/21-1260.pdf'>pdf</a>][<a href="/papers/v25/21-1260.bib">bib</a>]      [<a href="https://github.com/karl-hajjar/wide-networks">code</a>] </dl> <dl> <dt>Sharp analysis of power iteration for tensor PCA</dt> <dd>Yuchen Wu, Kangjie Zhou, 2024. [<a href='/papers/v25/24-0006.html'>abs</a>][<a target=_blank href='/papers/volume25/24-0006/24-0006.pdf'>pdf</a>][<a href="/papers/v25/24-0006.bib">bib</a>] </dl> <dl> <dt>On the Intrinsic Structures of Spiking Neural Networks</dt> <dd>Shao-Qun Zhang, Jia-Yi Chen, Jin-Hui Wu, Gao Zhang, Huan Xiong, Bin Gu, Zhi-Hua Zhou, 2024. [<a href='/papers/v25/23-1526.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1526/23-1526.pdf'>pdf</a>][<a href="/papers/v25/23-1526.bib">bib</a>] </dl> <dl> <dt>Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance</dt> <dd>Lisha Chen, Heshan Fernando, Yiming Ying, Tianyi Chen, 2024. [<a href='/papers/v25/23-1287.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1287/23-1287.pdf'>pdf</a>][<a href="/papers/v25/23-1287.bib">bib</a>]      [<a href="https://github.com/heshandevaka/Trade-Off-MOL">code</a>] </dl> <dl> <dt>Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data</dt> <dd>Wanli Hong, Shuyang Ling, 2024. [<a href='/papers/v25/23-1215.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1215/23-1215.pdf'>pdf</a>][<a href="/papers/v25/23-1215.bib">bib</a>]      [<a href="https://github.com/WanliHongC/Neural-Collapse">code</a>] </dl> <dl> <dt>Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables</dt> <dd>Feng Xie, Biwei Huang, Zhengming Chen, Ruichu Cai, Clark Glymour, Zhi Geng, Kun Zhang, 2024. [<a href='/papers/v25/23-1052.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1052/23-1052.pdf'>pdf</a>][<a href="/papers/v25/23-1052.bib">bib</a>] </dl> <dl> <dt>Classification of Data Generated by Gaussian Mixture Models Using Deep ReLU Networks</dt> <dd>Tian-Yi Zhou, Xiaoming Huo, 2024. [<a href='/papers/v25/23-0957.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0957/23-0957.pdf'>pdf</a>][<a href="/papers/v25/23-0957.bib">bib</a>] </dl> <dl> <dt>Differentially Private Topological Data Analysis</dt> <dd>Taegyu Kang, Sehwan Kim, Jinwon Sohn, Jordan Awan, 2024. [<a href='/papers/v25/23-0585.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0585/23-0585.pdf'>pdf</a>][<a href="/papers/v25/23-0585.bib">bib</a>]      [<a href="https://github.com/jwsohn612/DPTDA">code</a>] </dl> <dl> <dt>On the Optimality of Misspecified Spectral Algorithms</dt> <dd>Haobo Zhang, Yicheng Li, Qian Lin, 2024. [<a href='/papers/v25/23-0383.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0383/23-0383.pdf'>pdf</a>][<a href="/papers/v25/23-0383.bib">bib</a>] </dl> <dl> <dt>An Entropy-Based Model for Hierarchical Learning</dt> <dd>Amir R. Asadi, 2024. [<a href='/papers/v25/23-0096.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0096/23-0096.pdf'>pdf</a>][<a href="/papers/v25/23-0096.bib">bib</a>] </dl> <dl> <dt>Optimal Clustering with Bandit Feedback</dt> <dd>Junwen Yang, Zixin Zhong, Vincent Y. F. Tan, 2024. [<a href='/papers/v25/22-1088.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1088/22-1088.pdf'>pdf</a>][<a href="/papers/v25/22-1088.bib">bib</a>] </dl> <dl> <dt>A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression</dt> <dd>Youngseok Kim, Wei Wang, Peter Carbonetto, Matthew Stephens, 2024. [<a href='/papers/v25/22-0953.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0953/22-0953.pdf'>pdf</a>][<a href="/papers/v25/22-0953.bib">bib</a>]      [<a href="https://github.com/stephenslab/mr.ash.alpha">code</a>] </dl> <dl> <dt>Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks</dt> <dd>Yuval Belfer, Amnon Geifman, Meirav Galun, Ronen Basri, 2024. [<a href='/papers/v25/22-0597.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0597/22-0597.pdf'>pdf</a>][<a href="/papers/v25/22-0597.bib">bib</a>] </dl> <dl> <dt>Permuted and Unlinked Monotone Regression in R^d: an approach based on mixture modeling and optimal transport</dt> <dd>Martin Slawski, Bodhisattva Sen, 2024. [<a href='/papers/v25/22-0058.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0058/22-0058.pdf'>pdf</a>][<a href="/papers/v25/22-0058.bib">bib</a>] </dl> <dl> <dt>Volterra Neural Networks (VNNs)</dt> <dd>Siddharth Roheda, Hamid Krim, Bo Jiang, 2024. [<a href='/papers/v25/21-1082.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1082/21-1082.pdf'>pdf</a>][<a href="/papers/v25/21-1082.bib">bib</a>]      [<a href="https://github.com/sid-roheda/Volterra-Neural-Networks">code</a>] </dl> <dl> <dt>Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm</dt> <dd>Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton, 2024. [<a href='/papers/v25/23-1663.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1663/23-1663.pdf'>pdf</a>][<a href="/papers/v25/23-1663.bib">bib</a>] </dl> <dl> <dt>Bayesian Regression Markets</dt> <dd>Thomas Falconer, Jalal Kazempour, Pierre Pinson, 2024. [<a href='/papers/v25/23-1385.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1385/23-1385.pdf'>pdf</a>][<a href="/papers/v25/23-1385.bib">bib</a>]      [<a href="https://github.com/tdfalc/regression-markets">code</a>] </dl> <dl> <dt>Sharpness-Aware Minimization and the Edge of Stability</dt> <dd>Philip M. Long, Peter L. Bartlett, 2024. [<a href='/papers/v25/23-1285.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1285/23-1285.pdf'>pdf</a>][<a href="/papers/v25/23-1285.bib">bib</a>]      [<a href="https://github.com/google-deepmind/sam_edge">code</a>] </dl> <dl> <dt>Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization</dt> <dd>Sijia Chen, Yu-Jie Zhang, Wei-Wei Tu, Peng Zhao, Lijun Zhang, 2024. [<a href='/papers/v25/23-1072.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1072/23-1072.pdf'>pdf</a>][<a href="/papers/v25/23-1072.bib">bib</a>] </dl> <dl> <dt>Multi-Objective Neural Architecture Search by Learning Search Space Partitions</dt> <dd>Yiyang Zhao, Linnan Wang, Tian Guo, 2024. [<a href='/papers/v25/23-1013.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1013/23-1013.pdf'>pdf</a>][<a href="/papers/v25/23-1013.bib">bib</a>]      [<a href="https://github.com/aoiang/LaMOO">code</a>] </dl> <dl> <dt>Fermat Distances: Metric Approximation, Spectral Convergence, and Clustering Algorithms</dt> <dd>Nicolás García Trillos, Anna Little, Daniel McKenzie, James M. Murphy, 2024. [<a href='/papers/v25/23-0939.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0939/23-0939.pdf'>pdf</a>][<a href="/papers/v25/23-0939.bib">bib</a>]      [<a href="https://github.com/JamesMMurphy11/FermatDistances">code</a>] </dl> <dl> <dt>Spherical Rotation Dimension Reduction with Geometric Loss Functions</dt> <dd>Hengrui Luo, Jeremy E. Purvis, Didong Li, 2024. [<a href='/papers/v25/23-0547.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0547/23-0547.pdf'>pdf</a>][<a href="/papers/v25/23-0547.bib">bib</a>] </dl> <dl> <dt>A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks</dt> <dd>Yuxin Sun, Dong Lao, Anthony Yezzi, Ganesh Sundaramoorthi, 2024. [<a href='/papers/v25/23-0137.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0137/23-0137.pdf'>pdf</a>][<a href="/papers/v25/23-0137.bib">bib</a>]      [<a href="https://github.com/sunyx523/surprising-instabilities">code</a>] </dl> <dl> <dt>Two is Better Than One: Regularized Shrinkage of Large Minimum Variance Portfolios</dt> <dd>Taras Bodnar, Nestor Parolya, Erik Thorsen, 2024. [<a href='/papers/v25/22-1337.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1337/22-1337.pdf'>pdf</a>][<a href="/papers/v25/22-1337.bib">bib</a>] </dl> <dl> <dt>Decentralized Natural Policy Gradient with Variance Reduction for Collaborative Multi-Agent Reinforcement Learning</dt> <dd>Jinchi Chen, Jie Feng, Weiguo Gao, Ke Wei, 2024. [<a href='/papers/v25/22-1036.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1036/22-1036.pdf'>pdf</a>][<a href="/papers/v25/22-1036.bib">bib</a>] </dl> <dl> <dt>Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning</dt> <dd>Ilnura Usmanova, Yarden As, Maryam Kamgarpour, Andreas Krause, 2024. [<a href='/papers/v25/22-0878.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0878/22-0878.pdf'>pdf</a>][<a href="/papers/v25/22-0878.bib">bib</a>]      [<a href="https://github.com/lasgroup/lbsgd-rl">code</a>] </dl> <dl> <dt>Cluster-Adaptive Network A/B Testing: From Randomization to Estimation</dt> <dd>Yang Liu, Yifan Zhou, Ping Li, Feifang Hu, 2024. [<a href='/papers/v25/22-0192.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0192/22-0192.pdf'>pdf</a>][<a href="/papers/v25/22-0192.bib">bib</a>] </dl> <dl> <dt>On the Computational and Statistical Complexity of Over-parameterized Matrix Sensing</dt> <dd>Jiacheng Zhuo, Jeongyeol Kwon, Nhat Ho, Constantine Caramanis, 2024. [<a href='/papers/v25/21-1437.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1437/21-1437.pdf'>pdf</a>][<a href="/papers/v25/21-1437.bib">bib</a>] </dl> <dl> <dt>Optimization-based Causal Estimation from Heterogeneous Environments</dt> <dd>Mingzhang Yin, Yixin Wang, David M. Blei, 2024. [<a href='/papers/v25/21-1028.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1028/21-1028.pdf'>pdf</a>][<a href="/papers/v25/21-1028.bib">bib</a>]      [<a href="https://github.com/mingzhang-yin/CoCo">code</a>] </dl> <dl> <dt>Optimal Locally Private Nonparametric Classification with Public Data</dt> <dd>Yuheng Ma, Hanfang Yang, 2024. [<a href='/papers/v25/23-1563.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1563/23-1563.pdf'>pdf</a>][<a href="/papers/v25/23-1563.bib">bib</a>]      [<a href="https://github.com/Karlmyh/LPCT">code</a>] </dl> <dl> <dt>Learning to Warm-Start Fixed-Point Optimization Algorithms</dt> <dd>Rajiv Sambharya, Georgina Hall, Brandon Amos, Bartolomeo Stellato, 2024. [<a href='/papers/v25/23-1174.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1174/23-1174.pdf'>pdf</a>][<a href="/papers/v25/23-1174.bib">bib</a>]      [<a href="https://github.com/stellatogrp/l2ws">code</a>] </dl> <dl> <dt>Nonparametric Regression Using Over-parameterized Shallow ReLU Neural Networks</dt> <dd>Yunfei Yang, Ding-Xuan Zhou, 2024. [<a href='/papers/v25/23-0918.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0918/23-0918.pdf'>pdf</a>][<a href="/papers/v25/23-0918.bib">bib</a>] </dl> <dl> <dt>Nonparametric Copula Models for Multivariate, Mixed, and Missing Data</dt> <dd>Joseph Feldman, Daniel R. Kowal, 2024. [<a href='/papers/v25/23-0495.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0495/23-0495.pdf'>pdf</a>][<a href="/papers/v25/23-0495.bib">bib</a>]      [<a href="https://github.com/jfeldman396/GMCImpute">code</a>] </dl> <dl> <dt>An Analysis of Quantile Temporal-Difference Learning</dt> <dd>Mark Rowland, Rémi Munos, Mohammad Gheshlaghi Azar, Yunhao Tang, Georg Ostrovski, Anna Harutyunyan, Karl Tuyls, Marc G. Bellemare, Will Dabney, 2024. [<a href='/papers/v25/23-0154.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0154/23-0154.pdf'>pdf</a>][<a href="/papers/v25/23-0154.bib">bib</a>] </dl> <dl> <dt>Conformal Inference for Online Prediction with Arbitrary Distribution Shifts</dt> <dd>Isaac Gibbs, Emmanuel J. Candès, 2024. [<a href='/papers/v25/22-1218.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1218/22-1218.pdf'>pdf</a>][<a href="/papers/v25/22-1218.bib">bib</a>]      [<a href="https://github.com/isgibbs/DtACI">code</a>] </dl> <dl> <dt>More Efficient Estimation of Multivariate Additive Models Based on Tensor Decomposition and Penalization</dt> <dd>Xu Liu, Heng Lian, Jian Huang, 2024. [<a href='/papers/v25/22-0578.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0578/22-0578.pdf'>pdf</a>][<a href="/papers/v25/22-0578.bib">bib</a>] </dl> <dl> <dt>A Kernel Test for Causal Association via Noise Contrastive Backdoor Adjustment</dt> <dd>Robert Hu, Dino Sejdinovic, Robin J. Evans, 2024. [<a href='/papers/v25/21-1409.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1409/21-1409.pdf'>pdf</a>][<a href="/papers/v25/21-1409.bib">bib</a>]      [<a href="https://github.com/MrHuff/kgformula">code</a>] </dl> <dl> <dt>Assessing the Overall and Partial Causal Well-Specification of Nonlinear Additive Noise Models</dt> <dd>Christoph Schultheiss, Peter Bühlmann, 2024. [<a href='/papers/v25/23-1397.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1397/23-1397.pdf'>pdf</a>][<a href="/papers/v25/23-1397.bib">bib</a>]      [<a href="https://github.com/cschultheiss/nl_GOF">code</a>] </dl> <dl> <dt>Simple Cycle Reservoirs are Universal</dt> <dd>Boyu Li, Robert Simon Fong, Peter Tino, 2024. [<a href='/papers/v25/23-1075.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1075/23-1075.pdf'>pdf</a>][<a href="/papers/v25/23-1075.bib">bib</a>] </dl> <dl> <dt>On the Computational Complexity of Metropolis-Adjusted Langevin Algorithms for Bayesian Posterior Sampling</dt> <dd>Rong Tang, Yun Yang, 2024. [<a href='/papers/v25/23-0783.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0783/23-0783.pdf'>pdf</a>][<a href="/papers/v25/23-0783.bib">bib</a>] </dl> <dl> <dt>Generalization and Stability of Interpolating Neural Networks with Minimal Width</dt> <dd>Hossein Taheri, Christos Thrampoulidis, 2024. [<a href='/papers/v25/23-0422.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0422/23-0422.pdf'>pdf</a>][<a href="/papers/v25/23-0422.bib">bib</a>] </dl> <dl> <dt>Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression</dt> <dd>Jiading Liu, Lei Shi, 2024. [<a href='/papers/v25/22-1326.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1326/22-1326.pdf'>pdf</a>][<a href="/papers/v25/22-1326.bib">bib</a>] </dl> <dl> <dt>Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations</dt> <dd>Yuanyuan Wang, Wei Huang, Mingming Gong, Xi Geng, Tongliang Liu, Kun Zhang, Dacheng Tao, 2024. [<a href='/papers/v25/22-1159.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1159/22-1159.pdf'>pdf</a>][<a href="/papers/v25/22-1159.bib">bib</a>] </dl> <dl> <dt>Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning</dt> <dd>Maximilian Hüttenrauch, Gerhard Neumann, 2024. [<a href='/papers/v25/22-0564.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0564/22-0564.pdf'>pdf</a>][<a href="/papers/v25/22-0564.bib">bib</a>] </dl> <dl> <dt>Kernel Thinning</dt> <dd>Raaz Dwivedi, Lester Mackey, 2024. [<a href='/papers/v25/21-1334.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1334/21-1334.pdf'>pdf</a>][<a href="/papers/v25/21-1334.bib">bib</a>]      [<a href="https://github.com/microsoft/goodpoints">code</a>] </dl> <dl> <dt>Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions</dt> <dd>Xuxing Chen, Tesi Xiao, Krishnakumar Balasubramanian, 2024. [<a href='/papers/v25/23-1323.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1323/23-1323.pdf'>pdf</a>][<a href="/papers/v25/23-1323.bib">bib</a>] </dl> <dl> <dt>Variational Estimators of the Degree-corrected Latent Block Model for Bipartite Networks</dt> <dd>Yunpeng Zhao, Ning Hao, Ji Zhu, 2024. [<a href='/papers/v25/23-0984.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0984/23-0984.pdf'>pdf</a>][<a href="/papers/v25/23-0984.bib">bib</a>] </dl> <dl> <dt>Statistical Inference for Fairness Auditing</dt> <dd>John J. Cherian, Emmanuel J. Candès, 2024. [<a href='/papers/v25/23-0739.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0739/23-0739.pdf'>pdf</a>][<a href="/papers/v25/23-0739.bib">bib</a>]      [<a href="https://github.com/jjcherian/fairaudit">code</a>] </dl> <dl> <dt>Adjusted Wasserstein Distributionally Robust Estimator in Statistical Learning</dt> <dd>Yiling Xie, Xiaoming Huo, 2024. [<a href='/papers/v25/23-0379.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0379/23-0379.pdf'>pdf</a>][<a href="/papers/v25/23-0379.bib">bib</a>] </dl> <dl> <dt>DoWhy-GCM: An Extension of DoWhy for Causal Inference in Graphical Causal Models</dt> <dd>Patrick Blöbaum, Peter Götz, Kailash Budhathoki, Atalanti A. Mastakouri, Dominik Janzing, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/22-1258.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1258/22-1258.pdf'>pdf</a>][<a href="/papers/v25/22-1258.bib">bib</a>]      [<a href="https://github.com/py-why/dowhy">code</a>] </dl> <dl> <dt>Flexible Bayesian Product Mixture Models for Vector Autoregressions</dt> <dd>Suprateek Kundu, Joshua Lukemire, 2024. [<a href='/papers/v25/22-0717.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0717/22-0717.pdf'>pdf</a>][<a href="/papers/v25/22-0717.bib">bib</a>] </dl> <dl> <dt>A Variational Approach to Bayesian Phylogenetic Inference</dt> <dd>Cheng Zhang, Frederick A. Matsen IV, 2024. [<a href='/papers/v25/22-0348.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0348/22-0348.pdf'>pdf</a>][<a href="/papers/v25/22-0348.bib">bib</a>]      [<a href="https://github.com/zcrabbit/vbpi-torch">code</a>] </dl> <dl> <dt>Fat-Shattering Dimension of k-fold Aggregations</dt> <dd>Idan Attias, Aryeh Kontorovich, 2024. [<a href='/papers/v25/21-1193.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1193/21-1193.pdf'>pdf</a>][<a href="/papers/v25/21-1193.bib">bib</a>] </dl> <dl> <dt>Unified Binary and Multiclass Margin-Based Classification</dt> <dd>Yutong Wang, Clayton Scott, 2024. [<a href='/papers/v25/23-1599.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1599/23-1599.pdf'>pdf</a>][<a href="/papers/v25/23-1599.bib">bib</a>] </dl> <dl> <dt>Neural Feature Learning in Function Space</dt> <dd>Xiangxiang Xu, Lizhong Zheng, 2024. [<a href='/papers/v25/23-1202.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1202/23-1202.pdf'>pdf</a>][<a href="/papers/v25/23-1202.bib">bib</a>]      [<a href="https://github.com/XiangxiangXu/NFE">code</a>] </dl> <dl> <dt>PyGOD: A Python Library for Graph Outlier Detection</dt> <dd>Kay Liu, Yingtong Dou, Xueying Ding, Xiyang Hu, Ruitong Zhang, Hao Peng, Lichao Sun, Philip S. Yu, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0963.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0963/23-0963.pdf'>pdf</a>][<a href="/papers/v25/23-0963.bib">bib</a>]      [<a href="https://pygod.org">code</a>] </dl> <dl> <dt>Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria</dt> <dd>Tengyuan Liang, 2024. [<a href='/papers/v25/23-0651.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0651/23-0651.pdf'>pdf</a>][<a href="/papers/v25/23-0651.bib">bib</a>] </dl> <dl> <dt>Fixed points of nonnegative neural networks</dt> <dd>Tomasz J. Piotrowski, Renato L. G. Cavalcante, Mateusz Gabor, 2024. [<a href='/papers/v25/23-0167.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0167/23-0167.pdf'>pdf</a>][<a href="/papers/v25/23-0167.bib">bib</a>]      [<a href="https://github.com/mateuszgabor/nn_networks">code</a>] </dl> <dl> <dt>Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks</dt> <dd>Fanghui Liu, Leello Dadi, Volkan Cevher, 2024. [<a href='/papers/v25/22-1250.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1250/22-1250.pdf'>pdf</a>][<a href="/papers/v25/22-1250.bib">bib</a>] </dl> <dl> <dt>A Survey on Multi-player Bandits</dt> <dd>Etienne Boursier, Vianney Perchet, 2024. [<a href='/papers/v25/22-0643.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0643/22-0643.pdf'>pdf</a>][<a href="/papers/v25/22-0643.bib">bib</a>] </dl> <dl> <dt>Transport-based Counterfactual Models</dt> <dd>Lucas De Lara, Alberto González-Sanz, Nicholas Asher, Laurent Risser, Jean-Michel Loubes, 2024. [<a href='/papers/v25/21-1440.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1440/21-1440.pdf'>pdf</a>][<a href="/papers/v25/21-1440.bib">bib</a>]      [<a href="https://github.com/lucasdelara/PI-Fair">code</a>] </dl> <dl> <dt>Adaptive Latent Feature Sharing for Piecewise Linear Dimensionality Reduction</dt> <dd>Adam Farooq, Yordan P. Raykov, Petar Raykov, Max A. Little, 2024. [<a href='/papers/v25/21-0146.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0146/21-0146.pdf'>pdf</a>][<a href="/papers/v25/21-0146.bib">bib</a>]      [<a href="https://colab.research.google.com/drive/1KrrHmAu6mV7tutZtYnpEbVibxs4GCwIo?usp=sharing">code</a>] </dl> <dl> <dt>Topological Node2vec: Enhanced Graph Embedding via Persistent Homology</dt> <dd>Yasuaki Hiraoka, Yusuke Imoto, Théo Lacombe, Killian Meehan, Toshiaki Yachimura, 2024. [<a href='/papers/v25/23-1185.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1185/23-1185.pdf'>pdf</a>][<a href="/papers/v25/23-1185.bib">bib</a>]      [<a href="https://github.com/killianfmeehan/topological_node2vec">code</a>] </dl> <dl> <dt>Granger Causal Inference in Multivariate Hawkes Processes by Minimum Message Length</dt> <dd>Katerina Hlaváčková-Schindler, Anna Melnykova, Irene Tubikanec, 2024. [<a href='/papers/v25/23-1066.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1066/23-1066.pdf'>pdf</a>][<a href="/papers/v25/23-1066.bib">bib</a>]      [<a href="https://github.com/IreneTubikanec/MMLH">code</a>] </dl> <dl> <dt>Representation Learning via Manifold Flattening and Reconstruction</dt> <dd>Michael Psenka, Druv Pai, Vishal Raman, Shankar Sastry, Yi Ma, 2024. [<a href='/papers/v25/23-0615.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0615/23-0615.pdf'>pdf</a>][<a href="/papers/v25/23-0615.bib">bib</a>]      [<a href="https://github.com/michael-psenka/manifold-linearization">code</a>] </dl> <dl> <dt>Bagging Provides Assumption-free Stability</dt> <dd>Jake A. Soloff, Rina Foygel Barber, Rebecca Willett, 2024. [<a href='/papers/v25/23-0536.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0536/23-0536.pdf'>pdf</a>][<a href="/papers/v25/23-0536.bib">bib</a>]      [<a href="https://github.com/jake-soloff/subbagging-experiments">code</a>] </dl> <dl> <dt>Fairness guarantees in multi-class classification with demographic parity</dt> <dd>Christophe Denis, Romuald Elie, Mohamed Hebiri, François Hu, 2024. [<a href='/papers/v25/23-0322.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0322/23-0322.pdf'>pdf</a>][<a href="/papers/v25/23-0322.bib">bib</a>] </dl> <dl> <dt>Regimes of No Gain in Multi-class Active Learning</dt> <dd>Gan Yuan, Yunfan Zhao, Samory Kpotufe, 2024. [<a href='/papers/v25/23-0234.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0234/23-0234.pdf'>pdf</a>][<a href="/papers/v25/23-0234.bib">bib</a>] </dl> <dl> <dt>Learning Optimal Dynamic Treatment Regimens Subject to Stagewise Risk Controls</dt> <dd>Mochuan Liu, Yuanjia Wang, Haoda Fu, Donglin Zeng, 2024. [<a href='/papers/v25/23-0072.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0072/23-0072.pdf'>pdf</a>][<a href="/papers/v25/23-0072.bib">bib</a>] </dl> <dl> <dt>Margin-Based Active Learning of Classifiers</dt> <dd>Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice, 2024. [<a href='/papers/v25/22-1127.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1127/22-1127.pdf'>pdf</a>][<a href="/papers/v25/22-1127.bib">bib</a>] </dl> <dl> <dt>Random Subgraph Detection Using Queries</dt> <dd>Wasim Huleihel, Arya Mazumdar, Soumyabrata Pal, 2024. [<a href='/papers/v25/22-0395.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0395/22-0395.pdf'>pdf</a>][<a href="/papers/v25/22-0395.bib">bib</a>] </dl> <dl> <dt>Classification with Deep Neural Networks and Logistic Loss</dt> <dd>Zihan Zhang, Lei Shi, Ding-Xuan Zhou, 2024. [<a href='/papers/v25/22-0049.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0049/22-0049.pdf'>pdf</a>][<a href="/papers/v25/22-0049.bib">bib</a>] </dl> <dl> <dt>Spectral learning of multivariate extremes</dt> <dd>Marco Avella Medina, Richard A Davis, Gennady Samorodnitsky, 2024. [<a href='/papers/v25/21-1367.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1367/21-1367.pdf'>pdf</a>][<a href="/papers/v25/21-1367.bib">bib</a>] </dl> <dl> <dt>Sum-of-norms clustering does not separate nearby balls</dt> <dd>Alexander Dunlap, Jean-Christophe Mourrat, 2024. [<a href='/papers/v25/21-0495.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0495/21-0495.pdf'>pdf</a>][<a href="/papers/v25/21-0495.bib">bib</a>]      [<a href="https://github.com/ajdunlap/son-clustering-experiments">code</a>] </dl> <dl> <dt>An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization</dt> <dd>Guy Kornowski, Ohad Shamir, 2024. [<a href='/papers/v25/23-1159.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1159/23-1159.pdf'>pdf</a>][<a href="/papers/v25/23-1159.bib">bib</a>] </dl> <dl> <dt>Linear Distance Metric Learning with Noisy Labels</dt> <dd>Meysam Alishahi, Anna Little, Jeff M. Phillips, 2024. [<a href='/papers/v25/23-0791.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0791/23-0791.pdf'>pdf</a>][<a href="/papers/v25/23-0791.bib">bib</a>]      [<a href="https://github.com/meysamalishahi/Linear-Distance-Metric-Learning">code</a>] </dl> <dl> <dt>OpenBox: A Python Toolkit for Generalized Black-box Optimization</dt> <dd>Huaijun Jiang, Yu Shen, Yang Li, Beicheng Xu, Sixian Du, Wentao Zhang, Ce Zhang, Bin Cui, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0537.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0537/23-0537.pdf'>pdf</a>][<a href="/papers/v25/23-0537.bib">bib</a>]      [<a href="https://github.com/PKU-DAIR/open-box">code</a>] </dl> <dl> <dt>Generative Adversarial Ranking Nets</dt> <dd>Yinghua Yao, Yuangang Pan, Jing Li, Ivor W. Tsang, Xin Yao, 2024. [<a href='/papers/v25/23-0461.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0461/23-0461.pdf'>pdf</a>][<a href="/papers/v25/23-0461.bib">bib</a>]      [<a href="https://github.com/EvaFlower/GARNet">code</a>] </dl> <dl> <dt>Predictive Inference with Weak Supervision</dt> <dd>Maxime Cauchois, Suyash Gupta, Alnur Ali, John C. Duchi, 2024. [<a href='/papers/v25/23-0253.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0253/23-0253.pdf'>pdf</a>][<a href="/papers/v25/23-0253.bib">bib</a>] </dl> <dl> <dt>Functions with average smoothness: structure, algorithms, and learning</dt> <dd>Yair Ashlagi, Lee-Ad Gottlieb, Aryeh Kontorovich, 2024. [<a href='/papers/v25/23-0182.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0182/23-0182.pdf'>pdf</a>][<a href="/papers/v25/23-0182.bib">bib</a>] </dl> <dl> <dt>Differentially Private Data Release for Mixed-type Data via Latent Factor Models</dt> <dd>Yanqing Zhang, Qi Xu, Niansheng Tang, Annie Qu, 2024. [<a href='/papers/v25/22-1324.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1324/22-1324.pdf'>pdf</a>][<a href="/papers/v25/22-1324.bib">bib</a>] </dl> <dl> <dt>The Non-Overlapping Statistical Approximation to Overlapping Group Lasso</dt> <dd>Mingyu Qi, Tianxi Li, 2024. [<a href='/papers/v25/22-1105.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1105/22-1105.pdf'>pdf</a>][<a href="/papers/v25/22-1105.bib">bib</a>]      [<a href="https://github.com/MingyuQi1995/Code-for-The-Non-Overlapping-Statistical-Approximation-to-Overlapping-Group-Lasso">code</a>] </dl> <dl> <dt>Faster Rates of Differentially Private Stochastic Convex Optimization</dt> <dd>Jinyan Su, Lijie Hu, Di Wang, 2024. [<a href='/papers/v25/22-0079.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0079/22-0079.pdf'>pdf</a>][<a href="/papers/v25/22-0079.bib">bib</a>] </dl> <dl> <dt>Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization</dt> <dd>O. Deniz Akyildiz, Sotirios Sabanis, 2024. [<a href='/papers/v25/21-1423.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1423/21-1423.pdf'>pdf</a>][<a href="/papers/v25/21-1423.bib">bib</a>] </dl> <dl> <dt>Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits</dt> <dd>Junpei Komiyama, Edouard Fouché, Junya Honda, 2024. [<a href='/papers/v25/21-0916.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0916/21-0916.pdf'>pdf</a>][<a href="/papers/v25/21-0916.bib">bib</a>]      [<a href="https://github.com/edouardfouche/G-NS-MAB">code</a>] </dl> <dl> <dt>Stable Implementation of Probabilistic ODE Solvers</dt> <dd>Nicholas Krämer, Philipp Hennig, 2024. [<a href='/papers/v25/20-1423.html'>abs</a>][<a target=_blank href='/papers/volume25/20-1423/20-1423.pdf'>pdf</a>][<a href="/papers/v25/20-1423.bib">bib</a>] </dl> <dl> <dt>More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity</dt> <dd>Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund, 2024. [<a href='/papers/v25/23-1360.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1360/23-1360.pdf'>pdf</a>][<a href="/papers/v25/23-1360.bib">bib</a>] </dl> <dl> <dt>Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space</dt> <dd>Zhengdao Chen, 2024. [<a href='/papers/v25/23-1225.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1225/23-1225.pdf'>pdf</a>][<a href="/papers/v25/23-1225.bib">bib</a>] </dl> <dl> <dt>QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration</dt> <dd>Felix Chalumeau, Bryan Lim, Raphaël Boige, Maxime Allard, Luca Grillotti, Manon Flageat, Valentin Macé, Guillaume Richard, Arthur Flajolet, Thomas Pierrot, Antoine Cully, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-1027.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1027/23-1027.pdf'>pdf</a>][<a href="/papers/v25/23-1027.bib">bib</a>]      [<a href="https://github.com/adaptive-intelligent-robotics/QDax">code</a>] </dl> <dl> <dt>Random Forest Weighted Local Fréchet Regression with Random Objects</dt> <dd>Rui Qiu, Zhou Yu, Ruoqing Zhu, 2024. [<a href='/papers/v25/23-0811.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0811/23-0811.pdf'>pdf</a>][<a href="/papers/v25/23-0811.bib">bib</a>]      [<a href="https://github.com/RuiQiu01/Code_RFWLFR.git">code</a>] </dl> <dl> <dt>PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design</dt> <dd>Alexandre Duval, Victor Schmidt, Santiago Miret, Yoshua Bengio, Alex Hernández-García, David Rolnick, 2024. [<a href='/papers/v25/23-0680.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0680/23-0680.pdf'>pdf</a>][<a href="/papers/v25/23-0680.bib">bib</a>]      [<a href="https://github.com/vict0rsch/PhAST">code</a>] </dl> <dl> <dt>Unsupervised Anomaly Detection Algorithms on Real-world Data: How Many Do We Need?</dt> <dd>Roel Bouman, Zaharah Bukhsh, Tom Heskes, 2024. [<a href='/papers/v25/23-0570.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0570/23-0570.pdf'>pdf</a>][<a href="/papers/v25/23-0570.bib">bib</a>]      [<a href="https://github.com/RoelBouman/outlierdetection">code</a>] </dl> <dl> <dt>Multi-class Probabilistic Bounds for Majority Vote Classifiers with Partially Labeled Data</dt> <dd>Vasilii Feofanov, Emilie Devijver, Massih-Reza Amini, 2024. [<a href='/papers/v25/23-0121.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0121/23-0121.pdf'>pdf</a>][<a href="/papers/v25/23-0121.bib">bib</a>] </dl> <dl> <dt>Information Processing Equalities and the Information–Risk Bridge</dt> <dd>Robert C. Williamson, Zac Cranko, 2024. [<a href='/papers/v25/22-0988.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0988/22-0988.pdf'>pdf</a>][<a href="/papers/v25/22-0988.bib">bib</a>] </dl> <dl> <dt>Nonparametric Regression for 3D Point Cloud Learning</dt> <dd>Xinyi Li, Shan Yu, Yueying Wang, Guannan Wang, Li Wang, Ming-Jun Lai, 2024. [<a href='/papers/v25/22-0735.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0735/22-0735.pdf'>pdf</a>][<a href="/papers/v25/22-0735.bib">bib</a>]      [<a href="https://github.com/funstatpackages/TPST_matlab">code</a>] </dl> <dl> <dt>AMLB: an AutoML Benchmark</dt> <dd>Pieter Gijsbers, Marcos L. P. Bueno, Stefan Coors, Erin LeDell, Sébastien Poirier, Janek Thomas, Bernd Bischl, Joaquin Vanschoren, 2024. [<a href='/papers/v25/22-0493.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0493/22-0493.pdf'>pdf</a>][<a href="/papers/v25/22-0493.bib">bib</a>]      [<a href="https://github.com/openml/automlbenchmark">code</a>] </dl> <dl> <dt>Materials Discovery using Max K-Armed Bandit</dt> <dd>Nobuaki Kikkawa, Hiroshi Ohno, 2024. [<a href='/papers/v25/22-0186.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0186/22-0186.pdf'>pdf</a>][<a href="/papers/v25/22-0186.bib">bib</a>] </dl> <dl> <dt>Semi-supervised Inference for Block-wise Missing Data without Imputation</dt> <dd>Shanshan Song, Yuanyuan Lin, Yong Zhou, 2024. [<a href='/papers/v25/21-1504.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1504/21-1504.pdf'>pdf</a>][<a href="/papers/v25/21-1504.bib">bib</a>] </dl> <dl> <dt>Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization</dt> <dd>Peng Zhao, Yu-Jie Zhang, Lijun Zhang, Zhi-Hua Zhou, 2024. [<a href='/papers/v25/21-0748.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0748/21-0748.pdf'>pdf</a>][<a href="/papers/v25/21-0748.bib">bib</a>] </dl> <dl> <dt>Scaling Speech Technology to 1,000+ Languages</dt> <dd>Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, Michael Auli, 2024. [<a href='/papers/v25/23-1318.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1318/23-1318.pdf'>pdf</a>][<a href="/papers/v25/23-1318.bib">bib</a>]      [<a href="https://github.com/facebookresearch/fairseq/tree/main/examples/mms">code</a>] </dl> <dl> <dt>MAP- and MLE-Based Teaching</dt> <dd>Hans Ulrich Simon, Jan Arne Telle, 2024. [<a href='/papers/v25/23-1086.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1086/23-1086.pdf'>pdf</a>][<a href="/papers/v25/23-1086.bib">bib</a>] </dl> <dl> <dt>A General Framework for the Analysis of Kernel-based Tests</dt> <dd>Tamara Fernández, Nicolás Rivera, 2024. [<a href='/papers/v25/23-0985.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0985/23-0985.pdf'>pdf</a>][<a href="/papers/v25/23-0985.bib">bib</a>] </dl> <dl> <dt>Overparametrized Multi-layer Neural Networks: Uniform Concentration of Neural Tangent Kernel and Convergence of Stochastic Gradient Descent</dt> <dd>Jiaming Xu, Hanjing Zhu, 2024. [<a href='/papers/v25/23-0740.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0740/23-0740.pdf'>pdf</a>][<a href="/papers/v25/23-0740.bib">bib</a>] </dl> <dl> <dt>Sparse Representer Theorems for Learning in Reproducing Kernel Banach Spaces</dt> <dd>Rui Wang, Yuesheng Xu, Mingsong Yan, 2024. [<a href='/papers/v25/23-0645.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0645/23-0645.pdf'>pdf</a>][<a href="/papers/v25/23-0645.bib">bib</a>] </dl> <dl> <dt>Exploration of the Search Space of Gaussian Graphical Models for Paired Data</dt> <dd>Alberto Roverato, Dung Ngoc Nguyen, 2024. [<a href='/papers/v25/23-0295.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0295/23-0295.pdf'>pdf</a>][<a href="/papers/v25/23-0295.bib">bib</a>] </dl> <dl> <dt>The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective</dt> <dd>Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar, 2024. [<a href='/papers/v25/22-1312.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1312/22-1312.pdf'>pdf</a>][<a href="/papers/v25/22-1312.bib">bib</a>]      [<a href="https://github.com/nerdslab/augmentation-theory">code</a>] </dl> <dl> <dt>Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality</dt> <dd>Joshua Cutler, Mateo Díaz, Dmitriy Drusvyatskiy, 2024. [<a href='/papers/v25/22-0832.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0832/22-0832.pdf'>pdf</a>][<a href="/papers/v25/22-0832.bib">bib</a>] </dl> <dl> <dt>Minimax Rates for High-Dimensional Random Tessellation Forests</dt> <dd>Eliza O'Reilly, Ngoc Mai Tran, 2024. [<a href='/papers/v25/22-0673.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0673/22-0673.pdf'>pdf</a>][<a href="/papers/v25/22-0673.bib">bib</a>] </dl> <dl> <dt>Nonparametric Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networks</dt> <dd>Guohao Shen, Yuling Jiao, Yuanyuan Lin, Joel L. Horowitz, Jian Huang, 2024. [<a href='/papers/v25/22-0488.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0488/22-0488.pdf'>pdf</a>][<a href="/papers/v25/22-0488.bib">bib</a>] </dl> <dl> <dt>Spatial meshing for general Bayesian multivariate models</dt> <dd>Michele Peruzzi, David B. Dunson, 2024. [<a href='/papers/v25/22-0083.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0083/22-0083.pdf'>pdf</a>][<a href="/papers/v25/22-0083.bib">bib</a>]      [<a href="https://github.com/mkln/meshed">code</a>] </dl> <dl> <dt>A Semi-parametric Estimation of Personalized Dose-response Function Using Instrumental Variables</dt> <dd>Wei Luo, Yeying Zhu, Xuekui Zhang, Lin Lin, 2024. [<a href='/papers/v25/21-1181.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1181/21-1181.pdf'>pdf</a>][<a href="/papers/v25/21-1181.bib">bib</a>] </dl> <dl> <dt>Learning Non-Gaussian Graphical Models via Hessian Scores and Triangular Transport</dt> <dd>Ricardo Baptista, Rebecca Morrison, Olivier Zahm, Youssef Marzouk, 2024. [<a href='/papers/v25/21-0022.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0022/21-0022.pdf'>pdf</a>][<a href="/papers/v25/21-0022.bib">bib</a>]      [<a href="https://github.com/baptistar/SING">code</a>] </dl> <dl> <dt>On the Learnability of Out-of-distribution Detection</dt> <dd>Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu, 2024. [<a href='/papers/v25/23-1257.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1257/23-1257.pdf'>pdf</a>][<a href="/papers/v25/23-1257.bib">bib</a>] </dl> <dl> <dt>Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training</dt> <dd>Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan, 2024. [<a href='/papers/v25/23-1073.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1073/23-1073.pdf'>pdf</a>][<a href="/papers/v25/23-1073.bib">bib</a>]      [<a href="https://github.com/sail-sg/win">code</a>] </dl> <dl> <dt>On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains</dt> <dd>Yicheng Li, Zixiong Yu, Guhan Chen, Qian Lin, 2024. [<a href='/papers/v25/23-0866.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0866/23-0866.pdf'>pdf</a>][<a href="/papers/v25/23-0866.bib">bib</a>] </dl> <dl> <dt>Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions</dt> <dd>Maksim Velikanov, Dmitry Yarotsky, 2024. [<a href='/papers/v25/23-0698.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0698/23-0698.pdf'>pdf</a>][<a href="/papers/v25/23-0698.bib">bib</a>] </dl> <dl> <dt>ptwt - The PyTorch Wavelet Toolbox</dt> <dd>Moritz Wolter, Felix Blanke, Jochen Garcke, Charles Tapley Hoyt, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0636.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0636/23-0636.pdf'>pdf</a>][<a href="/papers/v25/23-0636.bib">bib</a>]      [<a href="https://github.com/v0lta/PyTorch-Wavelet-Toolbox">code</a>] </dl> <dl> <dt>Choosing the Number of Topics in LDA Models – A Monte Carlo Comparison of Selection Criteria</dt> <dd>Victor Bystrov, Viktoriia Naboka-Krell, Anna Staszewska-Bystrova, Peter Winker, 2024. [<a href='/papers/v25/23-0188.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0188/23-0188.pdf'>pdf</a>][<a href="/papers/v25/23-0188.bib">bib</a>]      [<a href="https://github.com/VikaNa/sBIC">code</a>] </dl> <dl> <dt>Functional Directed Acyclic Graphs</dt> <dd>Kuang-Yao Lee, Lexin Li, Bing Li, 2024. [<a href='/papers/v25/22-1038.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1038/22-1038.pdf'>pdf</a>][<a href="/papers/v25/22-1038.bib">bib</a>] </dl> <dl> <dt>Unlabeled Principal Component Analysis and Matrix Completion</dt> <dd>Yunzhen Yao, Liangzu Peng, Manolis C. Tsakiris, 2024. [<a href='/papers/v25/22-0816.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0816/22-0816.pdf'>pdf</a>][<a href="/papers/v25/22-0816.bib">bib</a>]      [<a href="https://github.com/yaoyzh/Unlabeled_PCA_NeurIPS2021">code</a>] </dl> <dl> <dt>Distributed Estimation on Semi-Supervised Generalized Linear Model</dt> <dd>Jiyuan Tu, Weidong Liu, Xiaojun Mao, 2024. [<a href='/papers/v25/22-0670.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0670/22-0670.pdf'>pdf</a>][<a href="/papers/v25/22-0670.bib">bib</a>] </dl> <dl> <dt>Towards Explainable Evaluation Metrics for Machine Translation</dt> <dd>Christoph Leiter, Piyawat Lertvittayakumjorn, Marina Fomicheva, Wei Zhao, Yang Gao, Steffen Eger, 2024. [<a href='/papers/v25/22-0416.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0416/22-0416.pdf'>pdf</a>][<a href="/papers/v25/22-0416.bib">bib</a>] </dl> <dl> <dt>Differentially private methods for managing model uncertainty in linear regression</dt> <dd>Víctor Peña, Andrés F. Barrientos, 2024. [<a href='/papers/v25/21-1536.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1536/21-1536.pdf'>pdf</a>][<a href="/papers/v25/21-1536.bib">bib</a>] </dl> <dl> <dt>Data Summarization via Bilevel Optimization</dt> <dd>Zalán Borsos, Mojmír Mutný, Marco Tagliasacchi, Andreas Krause, 2024. [<a href='/papers/v25/21-1132.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1132/21-1132.pdf'>pdf</a>][<a href="/papers/v25/21-1132.bib">bib</a>] </dl> <dl> <dt>Pareto Smoothed Importance Sampling</dt> <dd>Aki Vehtari, Daniel Simpson, Andrew Gelman, Yuling Yao, Jonah Gabry, 2024. [<a href='/papers/v25/19-556.html'>abs</a>][<a target=_blank href='/papers/volume25/19-556/19-556.pdf'>pdf</a>][<a href="/papers/v25/19-556.bib">bib</a>]      [<a href="https://github.com/avehtari/psis">code</a>] </dl> <dl> <dt>Policy Gradient Methods in the Presence of Symmetries and State Abstractions</dt> <dd>Prakash Panangaden, Sahand Rezaei-Shoshtari, Rosie Zhao, David Meger, Doina Precup, 2024. [<a href='/papers/v25/23-1415.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1415/23-1415.pdf'>pdf</a>][<a href="/papers/v25/23-1415.bib">bib</a>]      [<a href="https://github.com/sahandrez/homomorphic_policy_gradient">code</a>] </dl> <dl> <dt>Scaling Instruction-Finetuned Language Models</dt> <dd>Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, Jason Wei, 2024. [<a href='/papers/v25/23-0870.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0870/23-0870.pdf'>pdf</a>][<a href="/papers/v25/23-0870.bib">bib</a>] </dl> <dl> <dt>Tangential Wasserstein Projections</dt> <dd>Florian Gunsilius, Meng Hsuan Hsieh, Myung Jin Lee, 2024. [<a href='/papers/v25/23-0708.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0708/23-0708.pdf'>pdf</a>][<a href="/papers/v25/23-0708.bib">bib</a>]      [<a href="https://github.com/menghsuanhsieh/tangential-wasserstein-projection">code</a>] </dl> <dl> <dt>Learnability of Linear Port-Hamiltonian Systems</dt> <dd>Juan-Pablo Ortega, Daiying Yin, 2024. [<a href='/papers/v25/23-0450.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0450/23-0450.pdf'>pdf</a>][<a href="/papers/v25/23-0450.bib">bib</a>]      [<a href="https://github.com/YINDAIYING/Learnability-of-Linear-Port-Hamiltonian-Systems">code</a>] </dl> <dl> <dt>Off-Policy Action Anticipation in Multi-Agent Reinforcement Learning</dt> <dd>Ariyan Bighashdel, Daan de Geus, Pavol Jancura, Gijs Dubbelman, 2024. [<a href='/papers/v25/23-0413.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0413/23-0413.pdf'>pdf</a>][<a href="/papers/v25/23-0413.bib">bib</a>]      [<a href="https://github.com/tue-mps/OffPA2">code</a>] </dl> <dl> <dt>On Unbiased Estimation for Partially Observed Diffusions</dt> <dd>Jeremy Heng, Jeremie Houssineau, Ajay Jasra, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0347.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0347/23-0347.pdf'>pdf</a>][<a href="/papers/v25/23-0347.bib">bib</a>]      [<a href="https://github.com/jeremyhengjm/UnbiasedScore">code</a>] </dl> <dl> <dt>Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions</dt> <dd>Stanislas Ducotterd, Alexis Goujon, Pakshal Bohra, Dimitris Perdios, Sebastian Neumayer, Michael Unser, 2024. [<a href='/papers/v25/22-1347.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1347/22-1347.pdf'>pdf</a>][<a href="/papers/v25/22-1347.bib">bib</a>]      [<a href="https://github.com/StanislasDucotterd/Lipschitz_DSNN">code</a>] </dl> <dl> <dt>Mathematical Framework for Online Social Media Auditing</dt> <dd>Wasim Huleihel, Yehonathan Refael, 2024. [<a href='/papers/v25/22-1112.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1112/22-1112.pdf'>pdf</a>][<a href="/papers/v25/22-1112.bib">bib</a>] </dl> <dl> <dt>An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates</dt> <dd>Jessie Finocchiaro, Rafael M. Frongillo, Bo Waggoner, 2024. [<a href='/papers/v25/22-0743.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0743/22-0743.pdf'>pdf</a>][<a href="/papers/v25/22-0743.bib">bib</a>] </dl> <dl> <dt>Low-rank Variational Bayes correction to the Laplace method</dt> <dd>Janet van Niekerk, Haavard Rue, 2024. [<a href='/papers/v25/21-1405.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1405/21-1405.pdf'>pdf</a>][<a href="/papers/v25/21-1405.bib">bib</a>]      [<a href="https://github.com/JanetVN1201/Code_for_papers/tree/main/Low-rank%20VB%20correction%20to%20GA">code</a>] </dl> <dl> <dt>Scaling the Convex Barrier with Sparse Dual Algorithms</dt> <dd>Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H.S. Torr, M. Pawan Kumar, 2024. [<a href='/papers/v25/21-0076.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0076/21-0076.pdf'>pdf</a>][<a href="/papers/v25/21-0076.bib">bib</a>]      [<a href="https://github.com/oval-group/oval-bab">code</a>] </dl> <dl> <dt>Causal-learn: Causal Discovery in Python</dt> <dd>Yujia Zheng, Biwei Huang, Wei Chen, Joseph Ramsey, Mingming Gong, Ruichu Cai, Shohei Shimizu, Peter Spirtes, Kun Zhang, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0970.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0970/23-0970.pdf'>pdf</a>][<a href="/papers/v25/23-0970.bib">bib</a>]      [<a href="https://github.com/py-why/causal-learn">code</a>] </dl> <dl> <dt>Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics</dt> <dd>Noga Mudrik, Yenho Chen, Eva Yezerets, Christopher J. Rozell, Adam S. Charles, 2024. [<a href='/papers/v25/23-0777.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0777/23-0777.pdf'>pdf</a>][<a href="/papers/v25/23-0777.bib">bib</a>]      [<a href="https://github.com/dLDS-Decomposed-Linear-Dynamics">code</a>] </dl> <dl> <dt>Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification</dt> <dd>Natalie S. Frank, Jonathan Niles-Weed, 2024. [<a href='/papers/v25/23-0456.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0456/23-0456.pdf'>pdf</a>][<a href="/papers/v25/23-0456.bib">bib</a>] </dl> <dl> <dt>Data Thinning for Convolution-Closed Distributions</dt> <dd>Anna Neufeld, Ameer Dharamshi, Lucy L. Gao, Daniela Witten, 2024. [<a href='/papers/v25/23-0446.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0446/23-0446.pdf'>pdf</a>][<a href="/papers/v25/23-0446.bib">bib</a>]      [<a href="https://github.com/anna-neufeld/datathin_paper">code</a>] </dl> <dl> <dt>A projected semismooth Newton method for a class of nonconvex composite programs with strong prox-regularity</dt> <dd>Jiang Hu, Kangkang Deng, Jiayuan Wu, Quanzheng Li, 2024. [<a href='/papers/v25/23-0371.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0371/23-0371.pdf'>pdf</a>][<a href="/papers/v25/23-0371.bib">bib</a>] </dl> <dl> <dt>Revisiting RIP Guarantees for Sketching Operators on Mixture Models</dt> <dd>Ayoub Belhadji, Rémi Gribonval, 2024. [<a href='/papers/v25/23-0044.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0044/23-0044.pdf'>pdf</a>][<a href="/papers/v25/23-0044.bib">bib</a>] </dl> <dl> <dt>Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization</dt> <dd>Daniel LeJeune, Jiayu Liu, Reinhard Heckel, 2024. [<a href='/papers/v25/22-1197.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1197/22-1197.pdf'>pdf</a>][<a href="/papers/v25/22-1197.bib">bib</a>]      [<a href="https://github.com/MLI-lab/monotonic_risk_relationships">code</a>] </dl> <dl> <dt>Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks</dt> <dd>Dong-Young Lim, Sotirios Sabanis, 2024. [<a href='/papers/v25/22-0796.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0796/22-0796.pdf'>pdf</a>][<a href="/papers/v25/22-0796.bib">bib</a>] </dl> <dl> <dt>Axiomatic effect propagation in structural causal models</dt> <dd>Raghav Singal, George Michailidis, 2024. [<a href='/papers/v25/22-0285.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0285/22-0285.pdf'>pdf</a>][<a href="/papers/v25/22-0285.bib">bib</a>] </dl> <dl> <dt>Optimal First-Order Algorithms as a Function of Inequalities</dt> <dd>Chanwoo Park, Ernest K. Ryu, 2024. [<a href='/papers/v25/21-1256.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1256/21-1256.pdf'>pdf</a>][<a href="/papers/v25/21-1256.bib">bib</a>]      [<a href="https://github.com/chanwoo-park-official/A-star-map/">code</a>] </dl> <dl> <dt>Resource-Efficient Neural Networks for Embedded Systems</dt> <dd>Wolfgang Roth, Günther Schindler, Bernhard Klein, Robert Peharz, Sebastian Tschiatschek, Holger Fröning, Franz Pernkopf, Zoubin Ghahramani, 2024. [<a href='/papers/v25/18-566.html'>abs</a>][<a target=_blank href='/papers/volume25/18-566/18-566.pdf'>pdf</a>][<a href="/papers/v25/18-566.bib">bib</a>] </dl> <dl> <dt>Trained Transformers Learn Linear Models In-Context</dt> <dd>Ruiqi Zhang, Spencer Frei, Peter L. Bartlett, 2024. [<a href='/papers/v25/23-1042.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1042/23-1042.pdf'>pdf</a>][<a href="/papers/v25/23-1042.bib">bib</a>] </dl> <dl> <dt>Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees</dt> <dd>Nachuan Xiao, Xiaoyin Hu, Xin Liu, Kim-Chuan Toh, 2024. [<a href='/papers/v25/23-0576.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0576/23-0576.pdf'>pdf</a>][<a href="/papers/v25/23-0576.bib">bib</a>] </dl> <dl> <dt>Efficient Modality Selection in Multimodal Learning</dt> <dd>Yifei He, Runxiang Cheng, Gargi Balasubramaniam, Yao-Hung Hubert Tsai, Han Zhao, 2024. [<a href='/papers/v25/23-0439.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0439/23-0439.pdf'>pdf</a>][<a href="/papers/v25/23-0439.bib">bib</a>] </dl> <dl> <dt>A Multilabel Classification Framework for Approximate Nearest Neighbor Search</dt> <dd>Ville Hyvönen, Elias Jääsaari, Teemu Roos, 2024. [<a href='/papers/v25/23-0286.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0286/23-0286.pdf'>pdf</a>][<a href="/papers/v25/23-0286.bib">bib</a>]      [<a href="https://github.com/vioshyvo/JMLR2024">code</a>] </dl> <dl> <dt>Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization</dt> <dd>Lorenzo Pacchiardi, Rilwan A. Adewoyin, Peter Dueben, Ritabrata Dutta, 2024. [<a href='/papers/v25/23-0038.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0038/23-0038.pdf'>pdf</a>][<a href="/papers/v25/23-0038.bib">bib</a>]      [<a href="https://github.com/LoryPack/GenerativeNetworksScoringRulesProbabilisticForecasting">code</a>] </dl> <dl> <dt>Multiple Descent in the Multiple Random Feature Model</dt> <dd>Xuran Meng, Jianfeng Yao, Yuan Cao, 2024. [<a href='/papers/v25/22-1389.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1389/22-1389.pdf'>pdf</a>][<a href="/papers/v25/22-1389.bib">bib</a>] </dl> <dl> <dt>Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling</dt> <dd>Ye He, Tyler Farghly, Krishnakumar Balasubramanian, Murat A. Erdogdu, 2024. [<a href='/papers/v25/22-1198.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1198/22-1198.pdf'>pdf</a>][<a href="/papers/v25/22-1198.bib">bib</a>] </dl> <dl> <dt>Invariant and Equivariant Reynolds Networks</dt> <dd>Akiyoshi Sannai, Makoto Kawano, Wataru Kumagai, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/22-0891.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0891/22-0891.pdf'>pdf</a>][<a href="/papers/v25/22-0891.bib">bib</a>]      [<a href="https://github.com/makora9143/ReyNet">code</a>] </dl> <dl> <dt>Personalized PCA: Decoupling Shared and Unique Features</dt> <dd>Naichen Shi, Raed Al Kontar, 2024. [<a href='/papers/v25/22-0810.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0810/22-0810.pdf'>pdf</a>][<a href="/papers/v25/22-0810.bib">bib</a>]      [<a href="https://github.com/UMDataScienceLab/Personalized_PCA">code</a>] </dl> <dl> <dt>Survival Kernets: Scalable and Interpretable Deep Kernel Survival Analysis with an Accuracy Guarantee</dt> <dd>George H. Chen, 2024. [<a href='/papers/v25/22-0667.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0667/22-0667.pdf'>pdf</a>][<a href="/papers/v25/22-0667.bib">bib</a>]      [<a href="https://github.com/georgehc/survival-kernets">code</a>] </dl> <dl> <dt>On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control</dt> <dd>Amrit Singh Bedi, Anjaly Parayil, Junyu Zhang, Mengdi Wang, Alec Koppel, 2024. [<a href='/papers/v25/21-1343.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1343/21-1343.pdf'>pdf</a>][<a href="/papers/v25/21-1343.bib">bib</a>] </dl> <dl> <dt>Convergence for nonconvex ADMM, with applications to CT imaging</dt> <dd>Rina Foygel Barber, Emil Y. Sidky, 2024. [<a href='/papers/v25/21-0831.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0831/21-0831.pdf'>pdf</a>][<a href="/papers/v25/21-0831.bib">bib</a>]      [<a href="https://github.com/rinafb/ADMM_CT">code</a>] </dl> <dl> <dt>Distributed Gaussian Mean Estimation under Communication Constraints: Optimal Rates and Communication-Efficient Algorithms</dt> <dd>T. Tony Cai, Hongji Wei, 2024. [<a href='/papers/v25/21-0316.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0316/21-0316.pdf'>pdf</a>][<a href="/papers/v25/21-0316.bib">bib</a>] </dl> <dl> <dt>Sparse NMF with Archetypal Regularization: Computational and Robustness Properties</dt> <dd>Kayhan Behdin, Rahul Mazumder, 2024. [<a href='/papers/v25/21-0233.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0233/21-0233.pdf'>pdf</a>][<a href="/papers/v25/21-0233.bib">bib</a>]      [<a href="https://github.com/kayhanbehdin/SparseAA">code</a>] </dl> <dl> <dt>Deep Network Approximation: Beyond ReLU to Diverse Activation Functions</dt> <dd>Shijun Zhang, Jianfeng Lu, Hongkai Zhao, 2024. [<a href='/papers/v25/23-0912.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0912/23-0912.pdf'>pdf</a>][<a href="/papers/v25/23-0912.bib">bib</a>] </dl> <dl> <dt>Effect-Invariant Mechanisms for Policy Generalization</dt> <dd>Sorawit Saengkyongam, Niklas Pfister, Predrag Klasnja, Susan Murphy, Jonas Peters, 2024. [<a href='/papers/v25/23-0802.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0802/23-0802.pdf'>pdf</a>][<a href="/papers/v25/23-0802.bib">bib</a>] </dl> <dl> <dt>Pygmtools: A Python Graph Matching Toolkit</dt> <dd>Runzhong Wang, Ziao Guo, Wenzheng Pan, Jiale Ma, Yikai Zhang, Nan Yang, Qi Liu, Longxuan Wei, Hanxue Zhang, Chang Liu, Zetian Jiang, Xiaokang Yang, Junchi Yan, 2024. <a href="http://www.jmlr.org/mloss/">(Machine Learning Open Source Software Paper)</a> [<a href='/papers/v25/23-0572.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0572/23-0572.pdf'>pdf</a>][<a href="/papers/v25/23-0572.bib">bib</a>]      [<a href="https://github.com/Thinklab-SJTU/pygmtools">code</a>] </dl> <dl> <dt>Heterogeneous-Agent Reinforcement Learning</dt> <dd>Yifan Zhong, Jakub Grudzien Kuba, Xidong Feng, Siyi Hu, Jiaming Ji, Yaodong Yang, 2024. [<a href='/papers/v25/23-0488.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0488/23-0488.pdf'>pdf</a>][<a href="/papers/v25/23-0488.bib">bib</a>]      [<a href="https://github.com/PKU-MARL/HARL">code</a>] </dl> <dl> <dt>Sample-efficient Adversarial Imitation Learning</dt> <dd>Dahuin Jung, Hyungyu Lee, Sungroh Yoon, 2024. [<a href='/papers/v25/23-0314.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0314/23-0314.pdf'>pdf</a>][<a href="/papers/v25/23-0314.bib">bib</a>] </dl> <dl> <dt>Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent</dt> <dd>Benjamin Gess, Sebastian Kassing, Vitalii Konarovskyi, 2024. [<a href='/papers/v25/23-0220.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0220/23-0220.pdf'>pdf</a>][<a href="/papers/v25/23-0220.bib">bib</a>] </dl> <dl> <dt>Rates of convergence for density estimation with generative adversarial networks</dt> <dd>Nikita Puchkin, Sergey Samsonov, Denis Belomestny, Eric Moulines, Alexey Naumov, 2024. [<a href='/papers/v25/23-0062.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0062/23-0062.pdf'>pdf</a>][<a href="/papers/v25/23-0062.bib">bib</a>] </dl> <dl> <dt>Additive smoothing error in backward variational inference for general state-space models</dt> <dd>Mathis Chagneux, Elisabeth Gassiat, Pierre Gloaguen, Sylvain Le Corff, 2024. [<a href='/papers/v25/22-1392.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1392/22-1392.pdf'>pdf</a>][<a href="/papers/v25/22-1392.bib">bib</a>] </dl> <dl> <dt>Optimal Bump Functions for Shallow ReLU networks: Weight Decay, Depth Separation, Curse of Dimensionality</dt> <dd>Stephan Wojtowytsch, 2024. [<a href='/papers/v25/22-1296.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1296/22-1296.pdf'>pdf</a>][<a href="/papers/v25/22-1296.bib">bib</a>] </dl> <dl> <dt>Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees</dt> <dd>Alexander Terenin, David R. Burt, Artem Artemev, Seth Flaxman, Mark van der Wilk, Carl Edward Rasmussen, Hong Ge, 2024. [<a href='/papers/v25/22-1170.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1170/22-1170.pdf'>pdf</a>][<a href="/papers/v25/22-1170.bib">bib</a>]      [<a href="https://github.com/awav/conjugate-gradient-sparse-gp">code</a>] </dl> <dl> <dt>On Tail Decay Rate Estimation of Loss Function Distributions</dt> <dd>Etrit Haxholli, Marco Lorenzi, 2024. [<a href='/papers/v25/22-0846.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0846/22-0846.pdf'>pdf</a>][<a href="/papers/v25/22-0846.bib">bib</a>]      [<a href="https://github.com/ehaxholli/CTE">code</a>] </dl> <dl> <dt>Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces</dt> <dd>Hao Liu, Haizhao Yang, Minshuo Chen, Tuo Zhao, Wenjing Liao, 2024. [<a href='/papers/v25/22-0719.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0719/22-0719.pdf'>pdf</a>][<a href="/papers/v25/22-0719.bib">bib</a>] </dl> <dl> <dt>Post-Regularization Confidence Bands for Ordinary Differential Equations</dt> <dd>Xiaowu Dai, Lexin Li, 2024. [<a href='/papers/v25/22-0487.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0487/22-0487.pdf'>pdf</a>][<a href="/papers/v25/22-0487.bib">bib</a>] </dl> <dl> <dt>On the Generalization of Stochastic Gradient Descent with Momentum</dt> <dd>Ali Ramezani-Kebrya, Kimon Antonakopoulos, Volkan Cevher, Ashish Khisti, Ben Liang, 2024. [<a href='/papers/v25/22-0068.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0068/22-0068.pdf'>pdf</a>][<a href="/papers/v25/22-0068.bib">bib</a>] </dl> <dl> <dt>Pursuit of the Cluster Structure of Network Lasso: Recovery Condition and Non-convex Extension</dt> <dd>Shotaro Yagishita, Jun-ya Gotoh, 2024. [<a href='/papers/v25/21-1190.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1190/21-1190.pdf'>pdf</a>][<a href="/papers/v25/21-1190.bib">bib</a>] </dl> <dl> <dt>Iterate Averaging in the Quest for Best Test Error</dt> <dd>Diego Granziol, Nicholas P. Baskerville, Xingchen Wan, Samuel Albanie, Stephen Roberts, 2024. [<a href='/papers/v25/21-1125.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1125/21-1125.pdf'>pdf</a>][<a href="/papers/v25/21-1125.bib">bib</a>]      [<a href="https://github.com/diegogranziol/Gadam">code</a>] </dl> <dl> <dt>Nonparametric Inference under B-bits Quantization</dt> <dd>Kexuan Li, Ruiqi Liu, Ganggang Xu, Zuofeng Shang, 2024. [<a href='/papers/v25/20-075.html'>abs</a>][<a target=_blank href='/papers/volume25/20-075/20-075.pdf'>pdf</a>][<a href="/papers/v25/20-075.bib">bib</a>] </dl> <dl> <dt>Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box</dt> <dd>Ryan Giordano, Martin Ingram, Tamara Broderick, 2024. [<a href='/papers/v25/23-1015.html'>abs</a>][<a target=_blank href='/papers/volume25/23-1015/23-1015.pdf'>pdf</a>][<a href="/papers/v25/23-1015.bib">bib</a>]      [<a href="https://github.com/rgiordan/DADVIPaper">code</a>] </dl> <dl> <dt>On Sufficient Graphical Models</dt> <dd>Bing Li, Kyongwon Kim, 2024. [<a href='/papers/v25/23-0893.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0893/23-0893.pdf'>pdf</a>][<a href="/papers/v25/23-0893.bib">bib</a>] </dl> <dl> <dt>Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond</dt> <dd>Nathan Kallus, Xiaojie Mao, Masatoshi Uehara, 2024. [<a href='/papers/v25/23-0661.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0661/23-0661.pdf'>pdf</a>][<a href="/papers/v25/23-0661.bib">bib</a>]      [<a href="https://github.com/CausalML/LocalizedDebiasedMachineLearning">code</a>] </dl> <dl> <dt>On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks</dt> <dd>Sebastian Neumayer, Lénaïc Chizat, Michael Unser, 2024. [<a href='/papers/v25/23-0549.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0549/23-0549.pdf'>pdf</a>][<a href="/papers/v25/23-0549.bib">bib</a>] </dl> <dl> <dt>Improving physics-informed neural networks with meta-learned optimization</dt> <dd>Alex Bihlo, 2024. [<a href='/papers/v25/23-0356.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0356/23-0356.pdf'>pdf</a>][<a href="/papers/v25/23-0356.bib">bib</a>] </dl> <dl> <dt>A Comparison of Continuous-Time Approximations to Stochastic Gradient Descent</dt> <dd>Stefan Ankirchner, Stefan Perko, 2024. [<a href='/papers/v25/23-0237.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0237/23-0237.pdf'>pdf</a>][<a href="/papers/v25/23-0237.bib">bib</a>] </dl> <dl> <dt>Critically Assessing the State of the Art in Neural Network Verification</dt> <dd>Matthias König, Annelot W. Bosman, Holger H. Hoos, Jan N. van Rijn, 2024. [<a href='/papers/v25/23-0119.html'>abs</a>][<a target=_blank href='/papers/volume25/23-0119/23-0119.pdf'>pdf</a>][<a href="/papers/v25/23-0119.bib">bib</a>] </dl> <dl> <dt>Estimating the Minimizer and the Minimum Value of a Regression Function under Passive Design</dt> <dd>Arya Akhavan, Davit Gogolashvili, Alexandre B. Tsybakov, 2024. [<a href='/papers/v25/22-1396.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1396/22-1396.pdf'>pdf</a>][<a href="/papers/v25/22-1396.bib">bib</a>] </dl> <dl> <dt>Modeling Random Networks with Heterogeneous Reciprocity</dt> <dd>Daniel Cirkovic, Tiandong Wang, 2024. [<a href='/papers/v25/22-1317.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1317/22-1317.pdf'>pdf</a>][<a href="/papers/v25/22-1317.bib">bib</a>] </dl> <dl> <dt>Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment</dt> <dd>Zixian Yang, Xin Liu, Lei Ying, 2024. [<a href='/papers/v25/22-1251.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1251/22-1251.pdf'>pdf</a>][<a href="/papers/v25/22-1251.bib">bib</a>] </dl> <dl> <dt>On Efficient and Scalable Computation of the Nonparametric Maximum Likelihood Estimator in Mixture Models</dt> <dd>Yangjing Zhang, Ying Cui, Bodhisattva Sen, Kim-Chuan Toh, 2024. [<a href='/papers/v25/22-1120.html'>abs</a>][<a target=_blank href='/papers/volume25/22-1120/22-1120.pdf'>pdf</a>][<a href="/papers/v25/22-1120.bib">bib</a>]      [<a href="https://github.com/YangjingZhang/Dual-ALM-for-NPMLE">code</a>] </dl> <dl> <dt>Decorrelated Variable Importance</dt> <dd>Isabella Verdinelli, Larry Wasserman, 2024. [<a href='/papers/v25/22-0801.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0801/22-0801.pdf'>pdf</a>][<a href="/papers/v25/22-0801.bib">bib</a>] </dl> <dl> <dt>Model-Free Representation Learning and Exploration in Low-Rank MDPs</dt> <dd>Aditya Modi, Jinglin Chen, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, 2024. [<a href='/papers/v25/22-0687.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0687/22-0687.pdf'>pdf</a>][<a href="/papers/v25/22-0687.bib">bib</a>] </dl> <dl> <dt>Seeded Graph Matching for the Correlated Gaussian Wigner Model via the Projected Power Method</dt> <dd>Ernesto Araya, Guillaume Braun, Hemant Tyagi, 2024. [<a href='/papers/v25/22-0402.html'>abs</a>][<a target=_blank href='/papers/volume25/22-0402/22-0402.pdf'>pdf</a>][<a href="/papers/v25/22-0402.bib">bib</a>]      [<a href="https://github.com/ErnestoArayaV/Graph-matching-PPMGM">code</a>] </dl> <dl> <dt>Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization</dt> <dd>Shicong Cen, Yuting Wei, Yuejie Chi, 2024. [<a href='/papers/v25/21-1205.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1205/21-1205.pdf'>pdf</a>][<a href="/papers/v25/21-1205.bib">bib</a>] </dl> <dl> <dt>Power of knockoff: The impact of ranking algorithm, augmented design, and symmetric statistic</dt> <dd>Zheng Tracy Ke, Jun S. Liu, Yucong Ma, 2024. [<a href='/papers/v25/21-1137.html'>abs</a>][<a target=_blank href='/papers/volume25/21-1137/21-1137.pdf'>pdf</a>][<a href="/papers/v25/21-1137.bib">bib</a>] </dl> <dl> <dt>Lower Complexity Bounds of Finite-Sum Optimization Problems: The Results and Construction</dt> <dd>Yuze Han, Guangzeng Xie, Zhihua Zhang, 2024. [<a href='/papers/v25/21-0264.html'>abs</a>][<a target=_blank href='/papers/volume25/21-0264/21-0264.pdf'>pdf</a>][<a href="/papers/v25/21-0264.bib">bib</a>] </dl> <dl> <dt>On Truthing Issues in Supervised Classification</dt> <dd>Jonathan K. Su, 2024. [<a href='/papers/v25/19-301.html'>abs</a>][<a target=_blank href='/papers/volume25/19-301/19-301.pdf'>pdf</a>][<a href="/papers/v25/19-301.bib">bib</a>] </dl> <a href="/papers/">Full list</a> <table width="100%"> <tr> <td align="right">&copy <a target="_top" href="https://www.jmlr.org">JMLR</a> 2024. </td> </tr> </table> </div>  <a style="font-size: 0" rel="me" href="https://sigmoid.social/@jmlr">Mastodon</a> </body> </html>