Table of Contents

• Conference on Learning Theory 2025: PrefaceNika Haghtalab, Ankur Moitra. [doi]
• Open Problem: Regret Minimization in Heavy-Tailed Bandits with Unknown Distributional ParametersGianmarco Genalti, Alberto Maria Metelli. 1-5 [doi]
• Optimistic Q-learning for average reward and episodic reinforcement learning extended abstractPriyank Agrawal, Shipra Agrawal. 1 [doi]
• Computable learning of natural hypothesis classesSyed Akbari, Matthew Harrison-Trainor. 2-21 [doi]
• Better Private Distribution Testing by Leveraging Unverified Auxiliary DataMaryam Aliakbarpour, Arnav Burudgunte, Clément L. Canonne, Ronitt Rubinfeld. 22-63 [doi]
• Regret Bounds for Robust Online Decision MakingAlexander Appel, Vanessa Kosoy. 64-146 [doi]
• Simplifying Adversarially Robust PAC Learning With ToleranceHassan Ashtiani, Vinayak Pathak, Ruth Urner. 147-168 [doi]
• Computational Intractability of Strategizing against Online LearnersAngelos Assos, Yuval Dagan, Nived Rajaraman. 169-199 [doi]
• Testing Thresholds and Spectral Properties of High-Dimensional Random Toroidal Graphs via Edgeworth-Style ExpansionsSamuel Baguley, Andreas Göbel 0001, Marcus Pappik, Leon Schiller. 200-201 [doi]
• Faster Acceleration for Steepest DescentCedar Site Bai, Brian Bullins. 202-230 [doi]
• Thompson Sampling for Bandit Convex OptimisationAlireza Bakhtiari, Tor Lattimore, Csaba Szepesvári. 231-263 [doi]
• Metric Embeddings Beyond Bi-Lipschitz Distortion via Sherali-AdamsAinesh Bakshi, Vincent Cohen-Addad, Rajesh Jayaram, Sam Hopkins 0001, Silvio Lattanzi. 264-279 [doi]
• How to safely discard features based on aggregate SHAP valuesRobi Bhattacharjee, Karolin Frohnapfel, Ulrike von Luxburg. 280-314 [doi]
• Optimal Graph Reconstruction by Counting Connected Components in Induced SubgraphsHadley Black, Arya Mazumdar, Barna Saha, Yinzhan Xu. 315-343 [doi]
• Learning Partitions with Optimal Query and Round ComplexitiesHadley Black, Arya Mazumdar, Barna Saha. 344-374 [doi]
• A Distributional-Lifting Theorem for PAC LearningGuy Blanc, Jane Lange, Carmen Strassle, Li-Yang Tan. 375-379 [doi]
• Stability and List-Replicability for Agnostic LearnersAri Blondal, Shan Gao, Hamed Hatami, Pooya Hatami. 380-400 [doi]
• Proofs as Explanations: Short Certificates for Reliable PredictionsAvrim Blum, Steve Hanneke, Chirag Pabbaraju, Donya Saless. 401-420 [doi]
• Accelerating Proximal Gradient Descent via Silver StepsizesJinho Bok, Jason M. Altschuler. 421-453 [doi]
• Logarithmic regret of exploration in average reward Markov decision processesVictor Boone, Bruno Gaujal. 454-533 [doi]
• Partial and Exact Recovery of a Random Hypergraph from its Graph ProjectionGuy Bresler, Chenghao Guo, Yury Polyanskiy, Andrew Yao. 534-593 [doi]
• Computational Equivalence of Spiked Covariance and Spiked Wigner Models via Gram-Schmidt PerturbationGuy Bresler, Alina Harbuzova. 594-595 [doi]
• Of Dice and Games: A Theory of Generalized BoostingMarco Bressan 0002, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen. 596-640 [doi]
• A Fine-grained Characterization of PAC LearnabilityMarco Bressan 0002, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen. 641-676 [doi]
• On the Convergence of Min-Max Langevin Dynamics and AlgorithmYang Cai, Siddharth Mitra, Xiuyuan Wang, Andre Wibisono. 677-754 [doi]
• What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness (Extended Abstract)Yang Cai, Alkis Kalavasis, Katerina Mamali, Anay Mehrotra, Manolis Zampetakis. 755-756 [doi]
• Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regimeFrancesco Camilli, Daria Tieplova, Eleonora Bergamin, Jean Barbier. 757-798 [doi]
• Market Making without RegretNicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Luigi Foscari, Vinayak Pathak. 799-837 [doi]
• Towards Fair Representation: Clustering and ConsensusDiptarka Chakraborty, Kushagra Chatterjee, Debarati Das 0001, Tien Long Nguyen, Romina Nobahari. 838-853 [doi]
• Exploring Facets of Language Generation in the LimitMoses Charikar, Chirag Pabbaraju. 854-887 [doi]
• Deterministic Apple TastingZachary Chase 0001, Idan Mehalel. 888-923 [doi]
• DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy TheoryJerry Chee, Arturs Backurs, Rainie Heck, Li Zhang, Janardhan Kulkarni, Thomas Rothvoss, Sivakanth Gopi. 924-951 [doi]
• -4/7) Second-Order Oracle ComplexityLesi Chen, Chengchang Liu, Luo Luo, Jingzhao Zhang. 952-982 [doi]
• Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential PrivacyFan Chen, Alexander Rakhlin. 983-985 [doi]
• Predicting quantum channels over general product distributionsSitan Chen, Jaume de Dios Pont, Jun-Ting Hsieh, Hsin-Yuan Huang, Jane Lange, Jerry Li 0001. 986-1007 [doi]
• Improved sample upper and lower bounds for trace estimation of quantum state powersKean Chen, Qisheng Wang. 1008-1028 [doi]
• Learning general Gaussian mixtures with efficient score matchingSitan Chen, Vasilis Kontonis, Kulin Shah. 1029-1090 [doi]
• Algorithms for Sparse LPN and LSPN Against Low-noise (extended abstract)Xue Chen, Wenxuan Shu, Zhaienhe Zhou. 1091-1093 [doi]
• Optimization, Isoperimetric Inequalities, and Sampling via Lyapunov PotentialsAugust Y. Chen, Karthik Sridharan. 1094-1153 [doi]
• Heavy-tailed Estimation is Easier than Adversarial ContaminationYeshwanth Cherapanamjeri, Daniel Lee. 1154-1184 [doi]
• The Space Complexity of Learning-Unlearning Algorithms (extended abstract)Yeshwanth Cherapanamjeri, Sumegba Garg, Nived Rajaraman, Ayush Sekhari, Abhishek Shetty. 1185-1193 [doi]
• Quantum State and Unitary Learning Implies Circuit Lower BoundsNai-Hui Chia, Daniel Liang, Fang Song. 1194-1252 [doi]
• Stochastic block models with many communities and the Kesten-Stigum bound - extended abstractByron Chin, Elchanan Mossel, Youngtak Sohn, Alexander S. Wein. 1253-1258 [doi]
• Spherical DimensionBogdan Chornomaz, Shay Moran, Tom Waknine. 1259-1313 [doi]
• Lower Bounds for Greedy Teaching Set ConstructionsSpencer Compton, Chirag Pabbaraju, Nikita Zhivotovskiy. 1314-1329 [doi]
• Non-Euclidean High-Order Smooth Convex Optimization Extended AbstractJuan Pablo Contreras, Cristóbal Guzmán, David Martínez-Rubio. 1330 [doi]
• Low-dimensional Functions are Efficiently Learnable under Randomly Biased DistributionsElisabetta Cornacchia, Dan Mikulincer, Elchanan Mossel. 1331-1365 [doi]
• Non-Monetary Mechanism Design without Distributional Information: Using Scarce Audits Wisely (Extended Abstract)Yan Dai 0002, Moïse Blanchard, Patrick Jaillet. 1366-1367 [doi]
• Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on $\mathbb{SO}(d)$Amit Daniely. 1368-1379 [doi]
• Rate-Preserving Reductions for Blackwell ApproachabilityChristoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan. 1380-1414 [doi]
• Low-rank fine-tuning lies between lazy training and feature learningArif Kerem Dayi, Sitan Chen. 1415-1471 [doi]
• Learning Intersections of Two Margin Halfspaces under Factorizable DistributionsIlias Diakonikolas, Mingchen Ma, Lisheng Ren, Christos Tzamos. 1472-1530 [doi]
• Faster Algorithms for Agnostically Learning Disjunctions and their ImplicationsIlias Diakonikolas, Daniel M. Kane, Lisheng Ren. 1531-1558 [doi]
• A Proof of The Changepoint Detection Threshold Conjecture in Preferential Attachment ModelsHang Du, Shuyang Gong, Jiaming Xu. 1559-1563 [doi]
• From Fairness to Infinity: Outcome-Indistinguishable (Omni)Prediction in Evolving GraphsCynthia Dwork, Chris Hays, Nicole Immorlica, Juan C. Perdomo, Pranay Tankala. 1564-1637 [doi]
• Logarithmic Width Suffices for Robust MemorizationAmitsour Egosi, Gilad Yehudai, Ohad Shamir. 1638-1690 [doi]
• Detecting Arbitrary Planted Subgraphs in Random GraphsDor Elimelech, Wasim Huleihel. 1691-1798 [doi]
• Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data AugmentationMatthew Esmaili Mallory, Kevin Han Huang, Morgane Austern. 1799-1918 [doi]
• Learning Augmented Graph k-ClusteringChenglin Fan, Kijun Shin. 1919-1934 [doi]
• Trade-offs in Data Memorization via Strong Data Processing InequalitiesVitaly Feldman, Guy Kornowski, Xin Lyu 0003. 1935-1973 [doi]
• Approximating the total variation distance between spin systemsWeiming Feng 0001, Hongyang Liu, Minji Yang. 1974-2025 [doi]
• Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in ExplorationDylan J. Foster, Zakaria Mhammedi, Dhruv Rohatgi. 2026-2142 [doi]
• An uncertainty principle for Linear Recurrent Neural NetworksAlexandre François, Antonio Orvieto, Francis R. Bach. 2143-2187 [doi]
• Complexity of Injectivity and Verification of ReLU Neural Networks (Extended Abstract)Vincent Froese, Moritz Grillo, Martin Skutella. 2188-2189 [doi]
• Bayes correlated equilibria, no-regret dynamics in Bayesian games, and the price of anarchyKaito Fujii. 2190-2191 [doi]
• Gradient Methods with Online ScalingWenzhi Gao, Ya-Chi Chu, Yinyu Ye 0001, Madeleine Udell. 2192-2226 [doi]
• Computing High-dimensional Confidence Sets for Arbitrary DistributionsChao Gao, Liren Shan, Vaidehi Srinivas, Aravindan Vijayaraghavan. 2227-2269 [doi]
• Blackwell's Approachability with Approximation AlgorithmsDan Garber, Mhna Massalha. 2270-2290 [doi]
• Faster Low-Rank Approximation and Kernel Ridge Regression via the Block-Nyström MethodSachin Garg, Michal Derezinski. 2291-2325 [doi]
• Model predictive control is almost optimal for restless banditsNicolas Gast, Dheeraj Narasimha. 2326-2361 [doi]
• Computing Optimal Regularizers for Online Linear OptimizationKhashayar Gatmiry, Jon Schneider, Stefanie Jegelka. 2362-2402 [doi]
• Learning Mixtures of Gaussians Using Diffusion ModelsKhashayar Gatmiry, Jonathan A. Kelner, Holden Lee. 2403-2456 [doi]
• "All-Something-Nothing" Phase Transitions in Planted k-Factor Recovery (Extended Abstract)Julia Gaudio, Colin Sandon, Jiaming Xu, Dana Yang. 2457-2459 [doi]
• PREM: Privately Answering Statistical Queries with Relative ErrorBadih Ghazi, Cristóbal Guzmán, Pritish Kamath, Alexander Knop, Ravi Kumar 0001, Pasin Manurangsi, Sushant Sachdeva. 2460 [doi]
• Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizonMargalit Glasgow, Denny Wu, Joan Bruna. 2461-2539 [doi]
• Tight Bounds for Noisy Computation of High-Influence Functions, Connectivity, and ThresholdYuzhou Gu, Xin Li, Yinzhan Xu. 2540-2591 [doi]
• Agnostic Learning of Arbitrary ReLU Activation under Gaussian MarginalsAnxin Guo, Aravindan Vijayaraghavan. 2592-2631 [doi]
• Alternating Regret for Online Convex OptimizationSoumita Hait, Ping Li, Haipeng Luo, Mengxiao Zhang. 2632-2633 [doi]
• Data Selection for ERMsSteve Hanneke, Shay Moran, Alexander Shlimovich, Amir Yehudayoff. 2634-2665 [doi]
• Universal Rates of ERM for Agnostic LearningSteve Hanneke, Mingyue Xu. 2666-2703 [doi]
• Universal Rates for Multiclass Learning with Bandit FeedbackSteve Hanneke, Amirreza Shaeiri, Qian Zhang. 2704-2756 [doi]
• Compression Barriers in Autoregressive TransformersThemistoklis Haris, Krzysztof Onak. 2757-2785 [doi]
• On the query complexity of sampling from non-log-concave distributions (extended abstract)Yuchen He, Chihao Zhang. 2786-2787 [doi]
• Learning DNF through Generalized Fourier RepresentationsMohsen Heidari, Roni Khardon. 2788-2804 [doi]
• Noisy Group Testing in the Linear Regime: Exact Thresholds and EfficientLukas Hintze, Lena Krieg, Olga Scheftelowitsch, Haodong Zhu. 2805-2821 [doi]
• Improved Margin Generalization Bounds for Voting ClassifiersMikael Møller Høgsgaard, Kasper Green Larsen. 2822-2855 [doi]
• Polynomial low degree hardness for Broadcasting on Trees (Extended Abstract)Han Huang, Elchanan Mossel. 2856-2857 [doi]
• Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit FeedbackShinji Ito, Haipeng Luo, Taira Tsuchiya, Yue Wu. 2858-2892 [doi]
• Optimal Differentially Private Sampling of Unbounded GaussiansValentio Iverson, Gautam Kamath 0001, Argyris Mouzakis. 2893-2941 [doi]
• Local Regularizers Are Not Transductive LearnersSky Jafar, Julian Asilis, Shaddin Dughmi. 2942-2957 [doi]
• On the Minimax Regret of Sequential Probability Assignment via Square-Root EntropyZeyu Jia, Alexander Rakhlin, Yury Polyanskiy. 2958-3016 [doi]
• Regularized Dikin Walks for Sampling Truncated Logconcave Measures, Mixed Isoperimetry and Beyond Worst-Case AnalysisMinhui Jiang, Yuansi Chen. 3017-3078 [doi]
• Online Covariance Estimation in Nonsmooth Stochastic ApproximationLiwei Jiang, Abhishek Roy, Krishna Balasubramanian, Damek Davis, Dmitriy Drusvyatskiy, Sen Na. 3079-3123 [doi]
• Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex OptimizationRuichen Jiang, Devyani Maladkar, Aryan Mokhtari. 3124-3158 [doi]
• Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation (Extended Abstract)Jikai Jin, Vasilis Syrgkanis. 3159-3160 [doi]
• A Theory of Learning with Autoregressive Chain of ThoughtNirmit Joshi, Gal Vardi, Adam Block, Surbhi Goel, Zhiyuan Li 0005, Theodor Misiakiewicz, Nathan Srebro. 3161-3212 [doi]
• The Sample Complexity of Distributed Simple Binary Hypothesis Testing under Information ConstraintsHadi Kazemi, Ankit Pensia, Varun S. Jog. 3213-3214 [doi]
• Experimental Design for Semiparametric BanditsSeok-Jin Kim, Gi-Soo Kim, Min-hwan Oh. 3215-3252 [doi]
• Learning Constant-Depth Circuits in Malicious Noise ModelsAdam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan. 3253-3263 [doi]
• Efficiently learning and sampling multimodal distributions with data-based initializationFrederic Koehler, Holden Lee, Thuy Duong Vuong. 3264-3326 [doi]
• The Oracle Complexity of Simplex-based Matrix Games: Linear Separability and Nash EquilibriaGuy Kornowski, Ohad Shamir. 3327-3353 [doi]
• Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak RecoveryFilip Kovacevic, Yihan Zhang 0001, Marco Mondelli. 3354-3404 [doi]
• The Role of Environment Access in Agnostic Reinforcement Learning (Extended Abstract)Akshay Krishnamurthy, Gene Li, Ayush Sekhari. 3405-3406 [doi]
• Spike-and-Slab Posterior Sampling in High DimensionsSymantak Kumar, Purnamrita Sarkar, Kevin Tian, Yusong Zhu. 3407-3462 [doi]
• A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic AnalysisAkash Kumar 0010, Rahul Parhi, Mikhail Belkin. 3463-3485 [doi]
• Low coordinate degree algorithms II: Categorical signals and generalized stochastic block modelsDmitriy Kunisky. 3486-3526 [doi]
• Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious PlayJohn Lazarsfeld, Georgios Piliouras, Ryann Sim, Andre Wibisono. 3527-3577 [doi]
• The Fundamental Limits of Recovering Planted Subgraphs (extended abstract)Daniel Lee, Francisco Pernice, Amit Rajaraman, Ilias Zadik. 3578-3579 [doi]
• Robust random graph matching in Gaussian models via vector approximate message passingZhangsong Li. 3580-3581 [doi]
• Some easy optimization problems have the overlap-gap propertyShuangping Li, Tselil Schramm. 3582-3622 [doi]
• A Polynomial-time Algorithm for Online Sparse Linear Regression with Improved Regret Bound under Weaker ConditionsJunfan Li, Shizhong Liao, Zenglin Xu, Liqiang Nie. 3623-3670 [doi]
• Multi-Pass Memory Lower Bounds for Learning ProblemsQian Li, Shuo Wang, Jiapeng Zhang. 3671-3699 [doi]
• Private Realizable-to-Agnostic Transformation with Near-Optimal Sample ComplexityBo Li, Wei Wang, Peng Ye. 3700-3722 [doi]
• Low-dimensional adaptation of diffusion models: Convergence in total variation (extended abstract)Jiadong Liang, Zhihan Huang, Yuxin Chen. 3723-3729 [doi]
• Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of Φ-Mutual Information (Extended Abstract)Jiaming Liang, Siddharth Mitra, Andre Wibisono. 3730-3731 [doi]
• Decision Making in Hybrid Environments: A Model Aggregation ApproachHaolin Liu, Chen-Yu Wei, Julian Zimmert. 3732-3765 [doi]
• Robust Algorithms for Recovering Planted r-Colorable GraphsAnand Louis, Rameesh Paul, Prasad Raghavendra. 3766-3794 [doi]
• Sparsity-Based Interpolation of External, Internal and Swap RegretZhou Lu, Y. Jennifer Sun, Zhiyu Zhang. 3795-3828 [doi]
• Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear LossesJiuyao Lu, Aaron Roth 0001, Mirah Shi. 3829-3878 [doi]
• Identifiability and Estimation in High-Dimensional Nonparametric Latent Structure ModelsYichen Lyu, Pengkun Yang. 3879-3880 [doi]
• Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive AdversariesArnab Maiti, Zhiyuan Fan, Kevin G. Jamieson, Lillian J. Ratliff, Gabriele Farina. 3881-3932 [doi]
• Learning sparse generalized linear models with binary outcomes via iterative hard thresholdingNamiko Matsumoto, Arya Mazumdar. 3933-4032 [doi]
• Online Convex Optimization with a Separation OracleZakaria Mhammedi. 4033-4077 [doi]
• Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value FunctionsZakaria Mhammedi. 4078-4165 [doi]
• The Planted Spanning Tree Problems: Exact Overlap Characterization via Local Weak Convergence Extended AbstractMehrdad Moharrami, Cristopher Moore, Jiaming Xu 0002. 4166-4167 [doi]
• Beyond Worst-Case Online Classification: VC-Based Regret Bounds for Relaxed BenchmarksOmar Montasser, Abhishek Shetty, Nikita Zhivotovskiy. 4168-4202 [doi]
• Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation LearningAntoine Moulin, Gergely Neu, Luca Viano. 4203-4270 [doi]
• Are all models wrong? Fundamental limits in distribution-free empirical model falsificationManuel M. Müller, Yuetian Luo, Rina Foygel Barber. 4271-4308 [doi]
• Sharper Bounds for Chebyshev Moment Matching, with ApplicationsCameron Musco, Christopher Musco, Lucas Rosenblatt, Apoorv Vikram Singh. 4309-4358 [doi]
• Estimating stationary mass, frequency by frequencyMilind Nakul, Vidya Muthukumar, Ashwin Pananjady. 4359 [doi]
• Improved algorithms for learning quantum Hamiltonians, via flat polynomialsShyam Narayanan. 4360-4385 [doi]
• Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty MatchingQuan Nguyen, Shinji Ito, Junpei Komiyama, Nishant Mehta. 4386-4451 [doi]
• On the Hardness of Bandit LearningNataly Brukhim, Aldo Pacchiano, Miroslav Dudík, Robert E. Schapire. 4452-4485 [doi]
• Learning Algorithms in the LimitHristo Papazov, Nicolas Flammarion. 4486-4510 [doi]
• Differentially Private Synthetic Graphs Preserving Triangle-Motif CutsPan Peng, Hangyu Xu. 4511-4564 [doi]
• Recovering Labels from Crowdsourced Data: an Optimal and Polynomial-Time MethodEmmanuel Pilliat. 4565-4595 [doi]
• Optimal Robust Estimation under Local and Global Corruptions: Stronger Adversary and Smaller ErrorThanasis Pittas, Ankit Pensia. 4596-4639 [doi]
• Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter RegimesVictor S. Portella, Nicholas J. A. Harvey. 4640-4667 [doi]
• Linear Convergence of Diffusion Models Under the Manifold HypothesisPeter Potaptchik, Iskander Azangulov, George Deligiannidis. 4668-4685 [doi]
• Truthfulness of Decision-Theoretic Calibration MeasuresMingda Qiao, Eric Zhao 0003. 4686-4739 [doi]
• Generation through the lens of learning theoryVinod Raman, Jiaxun Li, Ambuj Tewari. 4740-4776 [doi]
• Metric Clustering and Graph Optimization Problems using Weak Comparison OraclesRahul Raychaudhury, Wen-Zhi Li, Syamantak Das, Sainyam Galhotra, Stavros Sintos. 4777-4830 [doi]
• Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract)Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster. 4831-4837 [doi]
• Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement LearningDhruv Rohatgi, Dylan J. Foster. 4838-4936 [doi]
• Can a calibration metric be both testable and actionable?Raphael Rossellini, Jake A. Soloff, Rina Foygel Barber, Zhimei Ren, Rebecca Willett. 4937-4972 [doi]
• Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offsAlexander Ryabchenko, Idan Attias, Daniel M. Roy 0001. 4973-5014 [doi]
• Improved Offline Contextual Bandits with Second-Order Bounds: Betting and FreezingJ. Jon Ryu, Jeongyeol Kwon, Benjamin Koppe, Kwang-Sung Jun. 5015-5053 [doi]
• New Lower Bounds for Non-Convex Stochastic Optimization through Divergence DecompositionEl Mehdi Saad, Wei-Cheng Lee, Francesco Orabona. 5054-5107 [doi]
• Depth Separations in Neural Networks: Separating the Dimension from the AccuracyItay Safran, Daniel Reichman 0001, Paul Valiant. 5108-5142 [doi]
• The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networksSholom Schechtman, Nicolas Schreuder. 5143-5172 [doi]
• Private List Learnability vs. Online List LearnabilitySteve Hanneke, Shay Moran, Hilla Schefler, Iska Tsubari. 5173-5213 [doi]
• Testing Juntas and Junta Subclasses with Relative ErrorXi Chen 0001, William Pires, Toniann Pitassi, Rocco A. Servedio. 5214-5245 [doi]
• Testing (Conditional) Mutual Information - Extended AbstractJan Seyfried, Sayantan Sen, Marco Tomamichel. 5246-5247 [doi]
• The title of the paperMax Simchowitz, Daniel Pfrommer, Ali Jadbabaie. 5248-5351 [doi]
• Community detection with the Bethe-HessianLudovic Stephan, Yizhe Zhu. 5352-5353 [doi]
• Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity Extended AbstractDominik Stöger, Yizhe Zhu. 5354-5355 [doi]
• Optimal Online Bookmaking for Any Number of OutcomesHadar Tal, Oron Sabag. 5356-5409 [doi]
• Beyond propagation of chaos: A stochastic algorithm for mean field optimizationChandan Tankala, Dheeraj Nagaraj, Anant Raj. 5410-5440 [doi]
• Optimal Scheduling of Dynamic TransportPanos Tsimpos, Zhi Ren 0003, Jakob Zech, Youssef Marzouk 0001. 5441-5505 [doi]
• Corrupted Learning Dynamics in GamesTaira Tsuchiya, Shinji Ito, Haipeng Luo. 5506-5552 [doi]
• Learning shallow quantum circuits with many-qubit gatesFrancisco Vasconcelos 0001, Hsin-Yuan Huang. 5553-5604 [doi]
• Black-Box Reductions for Decentralized Online Convex Optimization in Changing EnvironmentsYuanyu Wan. 5605-5631 [doi]
• Learning Compositional Functions with Transformers from Easy-to-Hard DataZixuan Wang, Eshaan Nichani, Alberto Bietti, Alex Damian, Daniel Hsu 0001, Jason D. Lee, Denny Wu. 5632-5711 [doi]
• Orthogonal Causal Calibration (Extended Abstract)Justin Whitehouse, Christopher Jung 0001, Vasilis Syrgkanis, Bryan Wilder, Zhiwei Steven Wu. 5712-5713 [doi]
• Time-Uniform Self-Normalized Concentration for Vector-Valued Processes (Extended Abstract)Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas. 5714-5715 [doi]
• Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality (Extended Abstract)Andre Wibisono. 5716-5717 [doi]
• Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent MemorizationYu-Han Wu, Pierre Marion, Gérard Biau, Claire Boyer. 5718-5756 [doi]
• Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and ApplicationsYizhou Xu, Antoine Maillard, Lenka Zdeborová, Florent Krzakala. 5757-5823 [doi]
• Generalization error bound for denoising score matching under relaxed manifold assumptionKonstantin Yakovlev, Nikita Puchkin. 5824-5891 [doi]
• Improved Algorithms for Effective Resistance Computation on GraphsYichun Yang, Ronghua Li, Meihao Liao, Guoren Wang. 5892-5920 [doi]
• Robustly Learning Monotone Generalized Linear Models via Data AugmentationNikos Zarifis, Puqian Wang, Ilias Diakonikolas, Jelena Diakonikolas. 5921-5990 [doi]
• Anytime Acceleration of Gradient DescentZihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen 0002. 5991-6013 [doi]
• Fast and Multiphase Rates for Nearest Neighbor ClassifiersPengkun Yang, Jingzhao Zhang. 6014-6015 [doi]
• Linear Bandits on Ellipsoids: Minimax Optimal AlgorithmsRaymond Zhang, Hedi Hadiji, Richard Combes. 6016-6040 [doi]
• Towards Fundamental Limits for Active Multi-distribution LearningChicheng Zhang, Yihan Zhou. 6041-6090 [doi]
• The Adaptive Complexity of Finding a Stationary PointHuanjian Zhou, Andi Han, Akiko Takeda, Masashi Sugiyama. 6091-6123 [doi]
• Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised ClassificationXiaohan Zhu, Nathan Srebro. 6124-6155 [doi]
• Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RLMatthew Zurek, Yudong Chen. 6156-6209 [doi]
• Open Problem: Fixed-Parameter Tractability of Zonotope ProblemsVincent Froese, Moritz Grillo, Christoph Hertrich, Martin Skutella. 6210-6214 [doi]
• Open Problem: Structure-Agnostic Minimax Risk for Partial Linear ModelYihong Gu. 6220-6224 [doi]
• Open Problem: Data Selection for Regression TasksSteve Hanneke, Shay Moran, Alexander Shlimovich, Amir Yehudayoff. 6225-6229 [doi]
• Open Problem: Optimal Instance-Dependent Sample Complexity for finding Nash Equilibrium in Two Player Zero-Sum Matrix gamesArnab Maiti. 6230-6234 [doi]