Table of Contents

• Preface [doi]
• Limits of Approximating the Median Treatment EffectRaghavendra Addanki, Siddharth Bhandari. 1-21 [doi]
• Majority-of-Three: The Simplest Optimal Learner?Ishaq Aden-Ali, Mikael Møller Høandgsgaard, Kasper Green Larsen, Nikita Zhivotovskiy. 22-45 [doi]
• Metalearning with Very Few Samples Per TaskMaryam Aliakbarpour, Konstantina Bairaktari, Gavin Brown 0003, Adam Smith, Nathan Srebro, Jonathan R. Ullman. 46-93 [doi]
• A Unified Characterization of Private Learnability via Graph TheoryNoga Alon, Shay Moran, Hilla Schefler, Amir Yehudayoff. 94-129 [doi]
• Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement LearningPhilip Amortila, Tongyi Cao, Akshay Krishnamurthy. 130-160 [doi]
• Fast parallel sampling under isoperimetryNima Anari, Sinho Chewi, Thuy Duong Vuong. 161-185 [doi]
• Two fundamental limits for uncertainty quantification in predictive inferenceFelipe Areces, Chen Cheng, John C. Duchi, Kuditipudi Rohith. 186-218 [doi]
• Mode Estimation with Partial FeedbackCharles Arnal, Vivien Cabannes, Vianney Perchet. 219-220 [doi]
• Universally Instance-Optimal Mechanisms for Private Statistical EstimationHilal Asi, John C. Duchi, Saminul Haque, Zewei Li, Feng Ruan. 221-259 [doi]
• Regularization and Optimal Multiclass LearningJulian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng. 260-310 [doi]
• The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed BanditsSepehr Assadi, Chen Wang. 311-358 [doi]
• Universal Rates for Regression: Separations between Cut-Off and Absolute LossIdan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas. 359-405 [doi]
• Learning Neural Networks with Sparse ActivationsPranjal Awasthi, Nishanth Dikkala, Pritish Kamath, Raghu Meka. 406-425 [doi]
• The SMART approach to instance-optimal online learningSiddhartha Banerjee, Alankrita Bhatt, Christina Lee Yu. 426 [doi]
• ∞ Geometry in Random Geometric Graphs: Suboptimality of Triangles and Cluster ExpansionKiril Bangachev, Guy Bresler. 427-497 [doi]
• Metric Clustering and MST with Strong and Weak Distance OraclesMohammadHossein Bateni, Prathamesh Dharangutte, Rajesh Jayaram, Chen Wang. 498-550 [doi]
• Correlated Binomial ProcessMoïse Blanchard, Doron Cohen, Aryeh Kontorovich. 551-595 [doi]
• On the Performance of Empirical Risk Minimization with Smoothed DataAdam Block, Alexander Rakhlin, Abhishek Shetty. 596-629 [doi]
• Errors are Robustly Tamed in Cumulative Knowledge ProcessesAnna M. Brandenberger, Cassandra Marcussen, Elchanan Mossel, Madhu Sudan 0001. 630-631 [doi]
• Thresholds for Reconstruction of Random Hypergraphs From Graph ProjectionsGuy Bresler, Chenghao Guo, Yury Polyanskiy. 632-647 [doi]
• A Theory of Interpretable ApproximationsMarco Bressan 0002, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen. 648-668 [doi]
• Efficient Algorithms for Learning Monophonic Halfspaces in GraphsMarco Bressan 0002, Emmanuel Esposito, Maximilian Thiessen. 669-696 [doi]
• Online Stackelberg Optimization via Nonlinear ControlWilliam Brown, Christos H. Papadimitriou, Tim Roughgarden. 697-749 [doi]
• Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended AbstractGavin Brown 0003, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith. 750-751 [doi]
• Computational-Statistical Gaps for Improper Learning in Sparse Linear RegressionRares-Darius Buhai, Jingqiu Ding, Stefan Tiegel. 752-771 [doi]
• The Price of Adaptivity in Stochastic Convex OptimizationYair Carmon, Oliver Hinder. 772-774 [doi]
• Information-theoretic generalization bounds for learning from quantum dataMatthias C. Caro, Tom Gur, Cambyse Rouzé, Daniel Stilck França, Sathyawageeswar Subramanian. 775-839 [doi]
• Non-Clashing Teaching Maps for Balls in GraphsJérémie Chalopin, Victor Chepoi, Fionn Mc Inerney, Sébastien Ratel. 840-875 [doi]
• Smoothed Analysis for Learning Concepts with Low Intrinsic DimensionGautam Chandrasekaran, Adam T. Klivans, Vasilis Kontonis, Raghu Meka, Konstantinos Stavropoulos. 876-922 [doi]
• Dual VC Dimension Obstructs Sample Compression by EmbeddingsZachary Chase 0001, Bogdan Chornomaz, Steve Hanneke, Shay Moran, Amir Yehudayoff. 923-946 [doi]
• On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved AnalysisLesi Chen, Jing Xu, Jingzhao Zhang. 947-980 [doi]
• A faster and simpler algorithm for learning shallow networksSitan Chen, Shyam Narayanan. 981-994 [doi]
• Near-Optimal Learning and Planning in Separated Latent MDPsFan Chen, Constantinos Daskalakis, Noah Golowich, Alexander Rakhlin. 995-1067 [doi]
• Scale-free Adversarial Reinforcement LearningMingyu Chen 0012, Xuezhou Zhang. 1068-1101 [doi]
• The power of an adversary in Glauber dynamicsByron Chin, Ankur Moitra, Elchanan Mossel, Colin Sandon. 1102-1124 [doi]
• Undetectable Watermarks for Language ModelsMiranda Christ, Sam Gunn, Or Zamir. 1125-1139 [doi]
• Risk-Sensitive Online Algorithms (Extended Abstract)Nicolas Christianson, Bo Sun 0004, Steven H. Low, Adam Wierman. 1140-1141 [doi]
• Statistical curriculum learning: An elimination algorithm achieving an oracle riskOmer Cohen, Ron Meir, Nir Weinberger. 1142-1199 [doi]
• Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold QueriesEdith Cohen, Xin Lyu 0002, Jelani Nelson, Tamás Sarlós, Uri Stemmer. 1200-1222 [doi]
• Learnability Gaps of Strategic ClassificationLee Cohen 0001, Yishay Mansour, Shay Moran, Han Shao. 1223-1259 [doi]
• Refined Sample Complexity for Markov Games with Independent Linear Function Approximation (Extended Abstract)Yan Dai 0002, Qiwen Cui, Simon S. Du. 1260-1261 [doi]
• Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract)Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna. 1262 [doi]
• Is Efficient PAC Learning Possible with an Oracle That Responds "Yes" or "No"?Constantinos Daskalakis, Noah Golowich. 1263-1307 [doi]
• Testable Learning of General Halfspaces with Adversarial Label NoiseIlias Diakonikolas, Daniel M. Kane, Sihan Liu, Nikos Zarifis. 1308-1335 [doi]
• Statistical Query Lower Bounds for Learning Truncated GaussiansIlias Diakonikolas, Daniel M. Kane, Thanasis Pittas, Nikos Zarifis. 1336-1363 [doi]
• Efficiently Learning One-Hidden-Layer ReLU Networks via SchurPolynomialsIlias Diakonikolas, Daniel M. Kane. 1364-1378 [doi]
• On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound PerspectiveDaniil Dmitriev, Kristóf Szabó, Amartya Sanyal. 1379-1398 [doi]
• Physics-informed machine learning as a kernel methodNathan Doumèche, Francis Bach, Gérard Biau, Claire Boyer. 1399-1450 [doi]
• Universal Lower Bounds and Optimal Rates: Achieving Minimax Clustering Error in Sub-Exponential Mixture ModelsMaximilien Dreveton, Alperen Gözeten, Matthias Grossglauser, Patrick Thiran. 1451-1485 [doi]
• An information-theoretic lower bound in time-uniform estimationJohn C. Duchi, Saminul Haque. 1486-1500 [doi]
• On sampling diluted Spin-Glasses using Glauber DynamicsCharilaos Efthymiou 0001, Kostas Zampetakis. 1501-1515 [doi]
• Minimax Linear Regression under the Quantile RiskAyoub El Hanchi, Chris J. Maddison, Murat A. Erdogdu. 1516-1572 [doi]
• The Real Price of Bandit Information in Multiclass ClassificationLiad Erez, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran. 1573-1598 [doi]
• Topological Expressivity of ReLU Neural NetworksEkin Ergen, Moritz Grillo. 1599-1642 [doi]
• Contraction of Markovian Operators in Orlicz Spaces and Error Bounds for Markov Chain Monte Carlo (Extended Abstract)Amedeo Roberto Esposito, Marco Mondelli. 1643-1645 [doi]
• Computation-information gap in high-dimensional clusteringBertrand Even, Christophe Giraud 0002, Nicolas Verzelen. 1646-1712 [doi]
• Online Newton Method for Bandit Convex Optimisation Extended AbstractHidde Fokkema, Dirk van der Hoeven, Tor Lattimore, Jack J. Mayo. 1713-1714 [doi]
• Agnostic Active Learning of Single Index Models with Linear Sample ComplexityAarshvi Gajjar, Wai Ming Tai, Xingyu Xu, Chinmay Hegde, Christopher Musco, Yi Li. 1715-1754 [doi]
• Safe Linear Bandits over Unknown PolytopesAditya Gangrade, Tianrui Chen, Venkatesh Saligrama. 1755-1795 [doi]
• Sampling Polytopes with Riemannian HMC: Faster Mixing via the Lewis Weights BarrierKhashayar Gatmiry, Jonathan A. Kelner, Santosh S. Vempala. 1796-1881 [doi]
• (ε, u)-Adaptive Regret Minimization in Heavy-Tailed BanditsGianmarco Genalti, Lupo Marsigli, Nicola Gatti 0001, Alberto Maria Metelli. 1882-1915 [doi]
• On Convex Optimization with Semi-Sensitive FeaturesBadih Ghazi, Pritish Kamath, Ravi Kumar 0001, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang. 1916-1938 [doi]
• Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few ActionsNoah Golowich, Ankur Moitra. 1939-1981 [doi]
• Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems extended abstractTomás González, Cristóbal Guzmán, Courtney Paquette. 1982 [doi]
• On Computationally Efficient Multi-Class CalibrationParikshit Gopalan, Lunjia Hu, Guy N. Rothblum. 1983-2026 [doi]
• Omnipredictors for regression and the approximate rank of convex functionsParikshit Gopalan, Princewill Okoroafor, Prasad Raghavendra, Abhishek Sherry, Mihir Singhal. 2027-2070 [doi]
• Identification of mixtures of discrete product distributions in near-optimal sample and time complexitySpencer L. Gordon, Erik Jahn, Bijan Mazaheri, Yuval Rabani, Leonard J. Schulman. 2071-2091 [doi]
• On the Computability of Robust PAC LearningPascale Gourdeau, Tosca Lechner, Ruth Urner. 2092-2121 [doi]
• Principal eigenstate classical shadowsDaniel Grier, Hakop Pashayan, Luke Schaeffer. 2122-2165 [doi]
• Community detection in the hypergraph stochastic block model and reconstruction on hypertreesYuzhou Gu, Aaradhya Pandey. 2166-2203 [doi]
• Stochastic Constrained Contextual Bandits via Lyapunov Optimization Based Estimation to Decision FrameworkHengquan Guo, Xin Liu. 2204-2231 [doi]
• Beyond Catoni: Sharper Rates for Heavy-Tailed and Robust Mean EstimationShivam Gupta, Samuel Hopkins, Eric C. Price. 2232-2269 [doi]
• Prediction from compression for models with infinite memory, with applications to hidden Markov and renewal processesYanjun Han, Tianze Jiang, Yihong Wu 0001. 2270-2307 [doi]
• The Star Number and Eluder Dimension: Elementary Observations About the Dimensions of DisagreementSteve Hanneke. 2308-2359 [doi]
• List Sample Compression and Uniform ConvergenceSteve Hanneke, Shay Moran, Tom Waknine. 2360-2388 [doi]
• Adversarially-Robust Inference on Trees via Belief PropagationSamuel B. Hopkins, Anqi Li. 2389-2417 [doi]
• On the sample complexity of parameter estimation in logistic regression with normal designDaniel Hsu 0001, Arya Mazumdar. 2418-2437 [doi]
• Faster Sampling without Isoperimetry via Diffusion-based Monte CarloXunpeng Huang, Difan Zou, Hanze Dong, Yi-An Ma, Tong Zhang. 2438-2493 [doi]
• Information-Theoretic Thresholds for the Alignments of Partially Correlated GraphsDong Huang, Xianwen Song, Pengkun Yang. 2494-2518 [doi]
• Reconstructing the Geometry of Random Geometric Graphs (Extended Abstract)Han Huang, Pakawut Jiradilok, Elchanan Mossel. 2519-2521 [doi]
• Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-WorldsShinji Ito, Taira Tsuchiya, Junya Honda. 2522-2563 [doi]
• Black-Box k-to-1-PCA Reductions: Theory and ApplicationsArun Jambulapati, Syamantak Kumar, Jerry Li 0001, Shourya Pandey, Ankit Pensia, Kevin Tian. 2564-2607 [doi]
• Closing the Computational-Query Depth Gap in Parallel Stochastic Convex OptimizationArun Jambulapati, Aaron Sidford, Kevin Tian. 2608-2643 [doi]
• Offline Reinforcement Learning: Role of State Aggregation and Trajectory DataZeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei. 2644-2719 [doi]
• Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein spaceYiheng Jiang, Sinho Chewi, Aram-Alexandre Pooladian. 2720-2721 [doi]
• Faster Spectral Density Estimation and Sparsification in the Nuclear Norm (Extended Abstract)Yujia Jin, Ishani Karmarkar, Christopher Musco, Aaron Sidford, Apoorv Vikram Singh. 2722 [doi]
• Some Constructions of Private, Efficient, and Optimal K-Norm and Elliptic Gaussian NoiseMatthew Joseph, Alexander Yu. 2723-2766 [doi]
• Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening (Extended Abstract)Alkis Kalavasis, Anay Mehrotra, Manolis Zampetakis. 2767 [doi]
• New Lower Bounds for Testing Monotonicity and Log Concavity of DistributionsYuqian Cheng, Daniel M. Kane, Zhicheng Zheng. 2768-2794 [doi]
• Choosing the p in Lp Loss: Adaptive Rates for Symmetric Mean EstimationYu-Chun Kao, Min Xu, Cun-Hui Zhang. 2795-2839 [doi]
• Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical GapsJonathan A. Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi. 2840-2886 [doi]
• Testable Learning with Distribution ShiftAdam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan. 2887-2943 [doi]
• Learning Intersections of Halfspaces with Distribution Shift: Improved Algorithms and SQ Lower BoundsAdam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan. 2944-2978 [doi]
• The title of the paperCaleb Koch, Carmen Strassle, Li-Yang Tan. 2979-3010 [doi]
• Convergence of Kinetic Langevin Monte Carlo on Lie groupsLingkai Kong, Molei Tao. 3011-3063 [doi]
• Active Learning with Simple QuestionsKontonis Vasilis, Mingchen Ma, Tzamos Christos. 3064-3098 [doi]
• Sampling from the Mean-Field Stationary DistributionYunbum Kook, Matthew Shunshi Zhang, Sinho Chewi, Murat A. Erdogdu, Mufan (Bill) Li. 3099-3136 [doi]
• Gaussian Cooling and Dikin Walks: The Interior-Point Method for Logconcave SamplingYunbum Kook, Santosh S. Vempala. 3137-3240 [doi]
• Simple online learning with consistent oracleAlexander Kozachinskiy, Tomasz Steifer. 3241-3256 [doi]
• Accelerated Parameter-Free Stochastic OptimizationItai Kreisler, Maor Ivgi, Oliver Hinder, Yair Carmon. 3257-3324 [doi]
• Better-than-KL PAC-Bayes BoundsIlja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona. 3325-3352 [doi]
• Inherent limitations of dimensions for characterizing learnability of distribution classesTosca Lechner, Shai Ben-David. 3353-3374 [doi]
• Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-WorldsJongyeong Lee, Junya Honda, Shinji Ito, Min-hwan Oh. 3375-3430 [doi]
• Minimax-optimal reward-agnostic exploration in reinforcement learningGen Li 0005, Yuling Yan, Yuxin Chen 0002, Jianqing Fan. 3431-3436 [doi]
• Optimistic Rates for Learning from Label ProportionsGene Li, Lin Chen, Adel Javanmard, Vahab Mirrokni. 3437-3474 [doi]
• Online Policy Optimization in Unknown Nonlinear SystemsYiheng Lin, James A. Preiss, Fengze Xie, Emile Anand, Soon Jo Chung, Yisong Yue, Adam Wierman. 3475-3522 [doi]
• The role of randomness in quantum state certification with unentangled measurementsYuhan Liu, Jayadev Acharya. 3523-3555 [doi]
• Spatial properties of Bayesian unsupervised treesLinxi Liu, Li Ma. 3556-3581 [doi]
• The Predicted-Updates Dynamic Model: Offline, Incremental, and Decremental to Fully Dynamic TransformationsQuanquan C. Liu, Vaidehi Srinivas. 3582-3641 [doi]
• Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing DynamicsBrendan Lucier, Sarath Pattathil, Aleksandrs Slivkins, Mengxiao Zhang. 3642-3643 [doi]
• Linear bandits with polylogarithmic minimax regretJosep Lumbreras, Marco Tomamichel. 3644-3682 [doi]
• Convergence of Gradient Descent with Small Initialization for Unregularized Matrix CompletionJianhao Ma, Salar Fattahi. 3683-3742 [doi]
• Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPsDavide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli. 3743-3774 [doi]
• Harmonics of Learning: Universal Fourier Features Emerge in Invariant NetworksGiovanni Luca Marchetti, Christopher J. Hillar, Danica Kragic, Sophia Sanborn. 3775-3797 [doi]
• Low-degree phase transitions for detecting a planted clique in sublinear timeJay Mardia, Kabir Aladin Verchand, Alexander S. Wein. 3798-3822 [doi]
• Fast, blind, and accurate: Tuning-free sparse regression with global linear convergenceClaudio Mayrink Verdun, Oleh Melnyk, Felix Krahmer, Peter Jung 0001. 3823-3872 [doi]
• Fundamental Limits of Non-Linear Low-Rank Matrix EstimationPierre Mergny, Justin Ko, Florent Krzakala, Lenka Zdeborová. 3873 [doi]
• Finding Super-spreaders in Network CascadesElchanan Mossel, Anirudh Sridhar. 3874-3914 [doi]
• Exact Mean Square Linear Stability Analysis for SGDRotem Mulayoff, Tomer Michaeli. 3915-3969 [doi]
• Optimistic Information Directed SamplingGergely Neu, Matteo Papini, Ludovic Schwartz. 3970-4006 [doi]
• Robust Distribution Learning with Local and Global Adversarial Corruptions (extended abstract)Sloan Nietert, Ziv Goldfeld, Soroosh Shafiee. 4007-4008 [doi]
• Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinationsKazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu. 4009-4081 [doi]
• Depth Separation in Norm-Bounded Infinite-Width Neural NetworksSuzanna Parkinson, Greg Ongie, Rebecca Willett, Ohad Shamir, Nathan Srebro. 4082-4114 [doi]
• The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent CommunicationKumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro. 4115-4157 [doi]
• The complexity of approximate (coarse) correlated equilibrium for incomplete information gamesBinghui Peng, Aviad Rubinstein. 4158-4184 [doi]
• The sample complexity of multi-distribution learningBinghui Peng. 4185-4204 [doi]
• The Sample Complexity of Simple Binary Hypothesis TestingAnkit Pensia, Varun S. Jog, Po-Ling Loh. 4205-4206 [doi]
• Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting CodesNaty Peter, Eliad Tsfadia, Jonathan R. Ullman. 4207-4239 [doi]
• Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of InteractivityAlireza Fathollah Pour, Hassan Ashtiani, Shahab Asoodeh. 4240-4275 [doi]
• Dimension-free Structured Covariance EstimationNikita Puchkin, Maxim V. Rakhuba. 4276-4306 [doi]
• On the Distance from Calibration in Sequential PredictionMingda Qiao, Letian Zheng. 4307-4357 [doi]
• Apple Tasting: Combinatorial Dimensions and Minimax RatesVinod Raman, Unique Subedi, Ananth Raman, Ambuj Tewari. 4358-4380 [doi]
• Online Learning with Set-valued FeedbackVinod Raman, Unique Subedi, Ambuj Tewari. 4381-4412 [doi]
• Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing DiffusionsYilong Qin, Andrej Risteski. 4413-4457 [doi]
• Online Structured Prediction with Fenchel-Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic LossShinsaku Sakaue, Han Bao 0002, Taira Tsuchiya, Taihei Oki. 4458-4486 [doi]
• Provable Advantage in Quantum PAC LearningWilfred Salmon, Sergii Strelchuk, Tom Gur. 4487-4510 [doi]
• Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential StabilitySergey Samsonov, Daniil Tiapkin, Alexey Naumov, Eric Moulines. 4511-4547 [doi]
• Adversarial Online Learning with Temporal Feedback GraphsKhashayar Gatmiry, Jon Schneider. 4548-4572 [doi]
• Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality (extended abstract)Siyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang. 4573 [doi]
• A Non-Adaptive Algorithm for the Quantitative Group Testing ProblemMahdi Soleymani, Tara Javidi. 4574-4592 [doi]
• Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithmVishwak Srinivasan, Andre Wibisono, Ashia C. Wilson. 4593-4635 [doi]
• A non-backtracking method for long matrix and tensor completionLudovic Stephan, Yizhe Zhu. 4636-4690 [doi]
• Second Order Methods for Bandit Optimization and ControlArun Sai Suggala, Y. Jennifer Sun, Praneeth Netrapalli, Elad Hazan. 4691-4763 [doi]
• Improved Hardness Results for Learning Intersections of HalfspacesStefan Tiegel. 4764-4786 [doi]
• Pruning is Optimal for Learning Sparse Features in High-DimensionsNuri Mert Vural, Murat A. Erdogdu. 4787-4861 [doi]
• Nearly Optimal Regret for Decentralized Online Convex OptimizationYuanyu Wan, Tong Wei, Mingli Song, Lijun Zhang. 4862-4888 [doi]
• Efficient Algorithms for Attributed Graph Alignment with Vanishing Edge Correlation Extended AbstractZiao Wang, Weina Wang 0001, Lele Wang 0001. 4889-4890 [doi]
• Nonlinear spiked covariance matrices and signal propagation in deep neural networksZhichao Wang, Denny Wu, Zhou Fan. 4891-4957 [doi]
• Optimal score estimation via empirical Bayes smoothingAndre Wibisono, Yihong Wu, Kaylee Yingxi Yang. 4958-4991 [doi]
• Oracle-Efficient Hybrid Online Learning with Unknown DistributionChanglong Wu, Jin Sima, Wojciech Szpankowski. 4992-5018 [doi]
• Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization EfficiencyJingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu. 5019-5073 [doi]
• Bridging the Gap: Rademacher Complexity in Robust and Standard GeneralizationJiancong Xiao, Ruoyu Sun, Qi Long, Weijie Su 0001. 5074-5075 [doi]
• Multiple-output composite quantile regression through an optimal transport lensXuzhi Yang, Tengyao Wang. 5076-5122 [doi]
• Top-K ranking with a monotone adversaryYuepeng Yang, Antares Chen, Lorenzo Orecchia, Cong Ma. 5123-5162 [doi]
• Counting Stars is Constant-Degree Optimal For Detecting Any Planted Subgraph: Extended AbstractXifan Yu, Ilias Zadik, Peiyuan Zhang. 5163-5165 [doi]
• Fast two-time-scale stochastic gradient method with applications in reinforcement learningSihan Zeng, Thinh T. Doan 0001. 5166-5212 [doi]
• Settling the sample complexity of online reinforcement learningZihan Zhang, Yuxin Chen 0002, Jason D. Lee, Simon S. Du. 5213-5219 [doi]
• Optimal Multi-Distribution LearningZihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee. 5220-5223 [doi]
• Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing (Extended Abstract)Yihan Zhang 0001, Hong Chang Ji, Ramji Venkataramanan, Marco Mondelli. 5224-5230 [doi]
• Gap-Free Clustering: Sensitivity and Robustness of SDPMatthew Zurek, Yudong Chen. 5231-5300 [doi]
• Open Problem: Can Local Regularization Learn All Multiclass Problems?Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng. 5301-5305 [doi]
• Open Problem: What is the Complexity of Joint Differential Privacy in Linear Contextual Bandits?Achraf Azize, Debabrota Basu. 5306-5311 [doi]
• Open Problem: Tight Characterization of Instance-Optimal Identity TestingClément L. Canonne. 5312-5316 [doi]
• Open Problem: Black-Box Reductions and Adaptive Gradient Methods for Nonconvex OptimizationXinyi Chen, Elad Hazan. 5317-5324 [doi]
• Open problem: Direct Sums in Learning TheorySteve Hanneke, Shay Moran, Tom Waknine. 5325-5329 [doi]
• Open Problem: Optimal Rates for Stochastic Decision-Theoretic Online Learning Under Differentially PrivacyBingshan Hu, Nishant A. Mehta. 5330-5334 [doi]
• Open Problem: Anytime Convergence Rate of Gradient DescentGuy Kornowski, Ohad Shamir. 5335-5339 [doi]
• Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement LearningSattar Vakili. 5340-5344 [doi]
• Open problem: Convergence of single-timescale mean-field Langevin descent-ascent for two-player zero-sum gamesGuillaume Wang, Lénaïc Chizat. 5345-5350 [doi]