Table of Contents

• Preface [doi]
• Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré InequalityAlireza Mousavi Hosseini, Tyler K. Farghly, Ye He, Krishna Balasubramanian, Murat A. Erdogdu. 1-35 [doi]
• Improved Discretization Analysis for Underdamped Langevin Monte CarloMatthew Shunshi Zhang, Sinho Chewi, Mufan (Bill) Li, Krishna Balasubramanian, Murat A. Erdogdu. 36-71 [doi]
• The One-Inclusion Graph Algorithm is not Always OptimalIshaq Aden-Ali, Yeshwanth Cherapanamjeri, Abhishek Shetty, Nikita Zhivotovskiy. 72-88 [doi]
• Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGDMatthew Faw, Litu Rout, Constantine Caramanis, Sanjay Shakkottai. 89-160 [doi]
• Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed AssumptionsBohan Wang, Huishuai Zhang, Zhiming Ma, Wei Chen 0034. 161-190 [doi]
• Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth ProblemsYunwen Lei. 191-227 [doi]
• The Sample Complexity of Approximate Rejection Sampling With Applications to Smoothed Online LearningAdam Block, Yury Polyanskiy. 228-273 [doi]
• Online Learning and Solving Infinite Games with an ERM OracleAngelos Assos, Idan Attias, Yuval Dagan, Constantinos Daskalakis, Maxwell K. Fishelson. 274-324 [doi]
• Online Learning in Dynamically Changing EnvironmentsChanglong Wu, Ananth Grama, Wojciech Szpankowski. 325-358 [doi]
• Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric PenaltiesDavid Martínez-Rubio, Sebastian Pokutta. 359-393 [doi]
• Bregman Deviations of Generic Exponential FamiliesSayak Ray Chowdhury, Patrick Saux, Odalric Maillard, Aditya Gopalan. 394-449 [doi]
• Bagging is an Optimal PAC LearnerKasper Green Larsen. 450-468 [doi]
• Community Detection in the Hypergraph SBM: Optimal Recovery Given the Similarity MatrixJulia Gaudio, Nirmit Joshi. 469-510 [doi]
• Find a witness or shatter: the landscape of computable PAC learningValentino Delle Rose, Alexander Kozachinskiy, Cristóbal Rojas, Tomasz Steifer. 511-524 [doi]
• Proper Losses, Moduli of Convexity, and Surrogate Regret BoundsHan Bao. 525-547 [doi]
• Beyond Parallel Pancakes: Quasi-Polynomial Time Guarantees for Non-Spherical Gaussian MixturesRares-Darius Buhai, David Steurer. 548-611 [doi]
• Online Reinforcement Learning in Stochastic Continuous-Time SystemsMohamad Kazem Shirani Faradonbeh, Mohamad Sadegh Shirani Faradonbeh. 612-656 [doi]
• Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader AlgorithmFang Kong, Canzhe Zhao, Shuai Li 0010. 657-673 [doi]
• Private Online Prediction from Experts: Separations and Faster RatesHilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar. 674-699 [doi]
• Improved Bounds for Multi-task Learning with Trace Norm RegularizationWeiwei Liu. 700-714 [doi]
• Local Glivenko-CantelliDoron Cohen, Aryeh Kontorovich. 715 [doi]
• Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approachGiacomo Greco, Maxence Noble, Giovanni Conforti, Alain Durmus. 716-746 [doi]
• Multitask Learning via Shared Features: Algorithms and HardnessKonstantina Bairaktari, Guy Blanc, Li-Yang Tan, Jonathan R. Ullman, Lydia Zakynthinou. 747-772 [doi]
• Optimal Prediction Using Expert Advice and Randomized Littlestone DimensionYuval Filmus, Steve Hanneke, Idan Mehalel, Shay Moran. 773-836 [doi]
• Uniqueness of BP fixed point for the Potts model and applications to community detectionYuzhou Gu, Yury Polyanskiy. 837-884 [doi]
• Weak Recovery Threshold for the Hypergraph Stochastic Block ModelYuzhou Gu, Yury Polyanskiy. 885-920 [doi]
• Statistical-Computational Tradeoffs in Mixed Sparse Linear RegressionGabriel Arpino, Ramji Venkataramanan. 921-986 [doi]
• VOQL: Towards Optimal Regret in Model-free RL with Nonlinear Function ApproximationAlekh Agarwal, Yujia Jin, Tong Zhang 0001. 987-1063 [doi]
• On Testing and Learning Quantum Junta ChannelsZongbo Bao, Penghui Yao. 1064-1094 [doi]
• Repeated Bilateral Trade Against a Smoothed AdversaryNicolò Cesa-Bianchi, Tommaso Renato Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi 0001. 1095-1130 [doi]
• On the Existence of a Complexity in Fixed Budget Bandit IdentificationRémy Degenne. 1131-1154 [doi]
• Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single NeuronWeihang Xu, Simon S. Du. 1155-1198 [doi]
• From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networksLuca Arnaboldi 0002, Ludovic Stephan, Florent Krzakala, Bruno Loureiro. 1199-1227 [doi]
• Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifoldSholom Schechtman, Daniil Tiapkin, Michael Muehlebach, Éric Moulines. 1228-1258 [doi]
• Projection-free Online Exp-concave OptimizationDan Garber, Ben Kretzu. 1259-1284 [doi]
• A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPsDirk van der Hoeven, Lukas Zierahn, Tal Lancewicki, Aviv Rosenberg 0002, Nicolò Cesa-Bianchi. 1285-1321 [doi]
• Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic TheoryAndrew J. Wagenmaker, Dylan J. Foster. 1322-1472 [doi]
• Improved dimension dependence of a proximal algorithm for samplingJiaoJiao Fan, Bo Yuan, Yongxin Chen. 1473-1521 [doi]
• Private Covariance Approximation and Eigenvalue-Gap Bounds for Complex Gaussian PerturbationsOren Mangoubi, Nisheeth K. Vishnoi. 1522-1587 [doi]
• Exponential Hardness of Reinforcement Learning with Linear Function ApproximationSihan Liu, Gaurav Mahajan, Daniel Kane, Shachar Lovett, Gellért Weisz, Csaba Szepesvári. 1588-1617 [doi]
• Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision MakingAdam Block, Max Simchowitz, Alexander Rakhlin. 1618-1665 [doi]
• Learning and Testing Latent-Tree Ising Models EfficientlyAnthimos Vardis Kandiros, Constantinos Daskalakis, Yuval Dagan, Davin Choo. 1666-1729 [doi]
• Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon SetsArun Ganesh, Abhradeep Thakurta, Jalaj Upadhyay. 1730-1773 [doi]
• Complexity of High-Dimensional Identity Testing with Coordinate Conditional SamplingAntonio Blanca, Zongchen Chen, Daniel Stefankovic, Eric Vigoda. 1774-1790 [doi]
• Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit AlgorithmsOsama A. Hanna, Lin Yang 0011, Christina Fragouli. 1791-1821 [doi]
• Quantum Channel Certification with Incoherent MeasurementsOmar Fawzi, Nicolas Flammarion, Aurélien Garivier, Aadil Oufkir. 1822-1884 [doi]
• List Online ClassificationShay Moran, Ohad Sharon, Iska Tsubari, Sivan Yosebashvili. 1885-1913 [doi]
• InfoNCE Loss Provably Learns Cluster-Preserving RepresentationsAdvait Parulekar, Liam Collins, Karthikeyan Shanmugam, Aryan Mokhtari, Sanjay Shakkottai. 1914-1961 [doi]
• Online Learning Guided Curvature Approximation: A Quasi-Newton Method with Global Non-Asymptotic Superlinear ConvergenceRuichen Jiang, Qiujiang Jin, Aryan Mokhtari. 1962-1992 [doi]
• Exploring Local Norms in Exp-concave Statistical LearningNikita Puchkin, Nikita Zhivotovskiy. 1993-2013 [doi]
• Learning Hidden Markov Models Using Conditional SamplesGaurav Mahajan, Sham M. Kakade, Akshay Krishnamurthy, Cyril Zhang. 2014-2066 [doi]
• A Second-Order Method for Stochastic Bandit Convex OptimisationTor Lattimore, András György 0001. 2067-2094 [doi]
• A Lower Bound for Linear and Kernel Regression with Adaptive CovariatesTor Lattimore. 2095-2113 [doi]
• Provable Benefits of Representational Transfer in Reinforcement LearningAlekh Agarwal, Yuda Song 0001, Wen Sun 0002, Kaiwen Wang, Mengdi Wang, Xuezhou Zhang. 2114-2187 [doi]
• Geodesically convex M-estimation in metric spacesVictor-Emmanuel Brunel. 2188-2210 [doi]
• Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification NoiseIlias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane, Puqian Wang, Nikos Zarifis. 2211-2239 [doi]
• Tighter PAC-Bayes Bounds Through Coin-BettingKyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona. 2240-2264 [doi]
• Inference on Strongly Identified Functionals of Weakly Identified FunctionsAndrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara. 2265 [doi]
• Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed NoiseZijian Liu, Jiawei Zhang, Zhengyuan Zhou. 2266-2290 [doi]
• 2 Convergence Guarantees without Identification or ClosednessAndrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara. 2291-2318 [doi]
• SQ Lower Bounds for Learning Mixtures of Separated and Bounded Covariance GaussiansIlias Diakonikolas, Daniel M. Kane, Thanasis Pittas, Nikos Zarifis. 2319-2349 [doi]
• Allocating Divisible Resources on Arms with Unknown and Random RewardsWenhao Li, Ningyuan Chen. 2350-2351 [doi]
• Semi-Random Sparse Recovery in Nearly-Linear TimeJonathan A. Kelner, Jerry Li 0001, Allen X. Liu, Aaron Sidford, Kevin Tian. 2352-2398 [doi]
• Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal SamplerSivakanth Gopi, Yin Tat Lee, Daogao Liu, Ruoqi Shen, Kevin Tian. 2399-2439 [doi]
• Detection-Recovery Gap for Planted Dense CyclesCheng Mao, Alexander S. Wein, Shenduo Zhang. 2440-2481 [doi]
• Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong GapRaef Bassily, Cristóbal Guzmán, Michael Menart. 2482-2508 [doi]
• Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave SamplingJason M. Altschuler, Kunal Talwar. 2509-2510 [doi]
• A Pretty Fast Algorithm for Adaptive Private Mean EstimationRohith Kuditipudi, John C. Duchi, Saminul Haque. 2511-2551 [doi]
• SGD learning on neural networks: leap complexity and saddle-to-saddle dynamicsEmmanuel Abbe, Enric Boix-Adserà, Theodor Misiakiewicz. 2552-2623 [doi]
• Optimal Scoring Rules for Multi-dimensional EffortJason D. Hartline, Liren Shan, Yingkai Li, Yifan Wu. 2624-2650 [doi]
• Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function ApproximationQiwen Cui, Kaiqing Zhang, Simon S. Du. 2651-2652 [doi]
• Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret BoundsShinji Ito, Kei Takemura. 2653-2677 [doi]
• On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial MonitoringDean Foster, Dylan J. Foster, Noah Golowich, Alexander Rakhlin. 2678-2792 [doi]
• Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function ApproximationYuanhao Wang, Qinghua Liu, Yu Bai 0017, Chi Jin 0001. 2793-2848 [doi]
• Tight Bounds on the Hardness of Learning Simple Nonparametric MixturesWai Ming Tai, Bryon Aragam. 2849 [doi]
• Information-Directed Selection for Top-Two AlgorithmsWei You, Chao Qin, Zihao Wang, Shuoguang Yang. 2850-2851 [doi]
• Accelerated and Sparse Algorithms for Approximate Personalized PageRank and BeyondDavid Martínez-Rubio, Elias Samuel Wirth, Sebastian Pokutta. 2852-2876 [doi]
• Toward L_∞Recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random FieldsKefan Dong, Tengyu Ma 0001. 2877-2918 [doi]
• Self-Directed Linear ClassificationIlias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis. 2919-2947 [doi]
• On the Lower Bound of Minimizing Polyak-Łojasiewicz functionsPengyun Yue, Cong Fang, Zhouchen Lin. 2948-2968 [doi]
• Curvature and complexity: Better lower bounds for geodesically convex optimizationChristopher Criscitiello, Nicolas Boumal. 2969-3013 [doi]
• A Nearly Tight Bound for Fitting an Ellipsoid to Gaussian Random PointsDaniel Kane, Ilias Diakonikolas. 3014-3028 [doi]
• Hardness of Agnostically Learning Halfspaces from Worst-Case Lattice ProblemsStefan Tiegel. 3029-3064 [doi]
• Testing of Index-Invariant Properties in the Huge Object ModelSourav Chakraborty 0001, Eldar Fischer, Arijit Ghosh, Gopinath Mishra, Sayantan Sen. 3065-3136 [doi]
• Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random DesignsMichal Derezinski. 3137-3172 [doi]
• Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin MaximizationSpencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro. 3173-3228 [doi]
• Simple Binary Hypothesis Testing under Local Differential Privacy and Communication ConstraintsAnkit Pensia, Amir-Reza Asadi, Varun S. Jog, Po-Ling Loh. 3229-3230 [doi]
• Geometric Barriers for Stable and Online Algorithms for Discrepancy MinimizationDavid Gamarnik, Eren C. Kizildag, Will Perkins 0001, Changji Xu. 3231-3263 [doi]
• Intrinsic dimensionality and generalization properties of the R-norm inductive biasNavid Ardeshir, Daniel J. Hsu, Clayton Hendrick Sanford. 3264-3303 [doi]
• Improved Dynamic Regret for Online Frank-WolfeYuanyu Wan, Lijun Zhang 0005, Mingli Song. 3304-3327 [doi]
• Online Nonconvex Optimization with Limited Instantaneous Oracle FeedbackZiwei Guan, Yi Zhou 0017, Yingbin Liang. 3328-3355 [doi]
• Tackling Combinatorial Distribution Shift: A Matrix Completion PerspectiveMax Simchowitz, Abhishek Gupta 0004, Kaiqing Zhang. 3356-3468 [doi]
• The k-Cap Process on Geometric Random GraphsMirabel E. Reid, Santosh S. Vempala. 3469-3509 [doi]
• Efficient Algorithms for Sparse Moment Problems without SeparationZhiyuan Fan, Jian Li. 3510-3565 [doi]
• From Pseudorandomness to Multi-Group Fairness and BackCynthia Dwork, Daniel Lee, Huijia Lin, Pranay Tankala. 3566-3614 [doi]
• A new ranking scheme for modern data and its application to two-sample hypothesis testingDoudou Zhou, Hao Chen. 3615-3668 [doi]
• Linearization Algorithms for Fully Composite OptimizationMaria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion. 3669-3695 [doi]
• Near Optimal Heteroscedastic Regression with Symbiotic LearningAniket Das, Dheeraj M. Nagaraj, Praneeth Netrapalli, Dheeraj Baby. 3696-3757 [doi]
• Approximately Stationary Bandits with KnapsacksGiannis Fikioris, Éva Tardos. 3758-3782 [doi]
• Lower Bounds for the Convergence of Tensor Power Iteration on Random Overcomplete ModelsYuchen Wu, Kangjie Zhou. 3783-3820 [doi]
• Causal Matrix CompletionAnish Agarwal, Munther A. Dahleh, Devavrat Shah, Dennis Shen. 3821-3826 [doi]
• A High-dimensional Convergence Theorem for U-statistics with Applications to Kernel-based TestingKevin H. Huang, Xing Liu, Andrew B. Duncan, Axel Gandy. 3827-3918 [doi]
• Asymptotic confidence sets for random linear programsShuyu Liu, Florentina Bunea, Jonathan Niles-Weed. 3919-3940 [doi]
• Algorithmically Effective Differentially Private Synthetic DataYiyun He, Roman Vershynin, Yizhe Zhu. 3941-3968 [doi]
• Tight Guarantees for Interactive Decision Making with the Decision-Estimation CoefficientDylan J. Foster, Noah Golowich, Yanjun Han. 3969-4043 [doi]
• Reaching Kesten-Stigum Threshold in the Stochastic Block Model under Node CorruptionsYiding Hua, Jingqiu Ding, Tommaso d'Orsi, David Steurer. 4044-4071 [doi]
• Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster AlgorithmsAniket Das, Dheeraj M. Nagaraj, Anant Raj. 4072-4129 [doi]
• The Expressive Power of Tuning Only the Normalization LayersAngeliki Giannou, Shashank Rajput, Dimitris Papailiopoulos. 4130-4131 [doi]
• Precise Asymptotic Analysis of Deep Random Feature ModelsDavid Bosch, Ashkan Panahi, Babak Hassibi. 4132-4179 [doi]
• The Complexity of Markov Equilibrium in Stochastic GamesConstantinos Daskalakis, Noah Golowich, Kaiqing Zhang. 4180-4234 [doi]
• Near-optimal fitting of ellipsoids to random pointsAaron Potechin, Paxton M. Turner, Prayaag Venkat, Alexander S. Wein. 4235-4295 [doi]
• Entropic characterization of optimal rates for learning Gaussian mixturesZeyu Jia, Yury Polyanskiy, Yihong Wu 0001. 4296-4335 [doi]
• Minimizing Dynamic Regret on Geodesic Metric SpacesZihao Hu, Guanghui Wang, Jacob D. Abernethy. 4336-4383 [doi]
• Sharp analysis of EM for learning mixtures of pairwise differencesAbhishek Dhawan, Cheng Mao, Ashwin Pananjady. 4384-4428 [doi]
• Zeroth-order Optimization with Weak Dimension DependencyPengyun Yue, Long Yang, Cong Fang, Zhouchen Lin. 4429-4472 [doi]
• Quasi-Newton Steps for Efficient Online Exp-Concave OptimizationZakaria Mhammedi, Khashayar Gatmiry. 4473-4503 [doi]
• Condition-number-independent Convergence Rate of Riemannian Hamiltonian Monte Carlo with Numerical IntegratorsYunbum Kook, Yin Tat Lee, Ruoqi Shen, Santosh S. Vempala. 4504-4569 [doi]
• Deterministic Nonsmooth Nonconvex OptimizationMichael I. Jordan, Guy Kornowski, Tianyi Lin, Ohad Shamir, Manolis Zampetakis. 4570-4597 [doi]
• Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) LearningZeyuan Allen Zhu, Yuanzhi Li. 4598 [doi]
• Differentially Private and Lazy Online Convex OptimizationNaman Agarwal, Satyen Kale, Karan Singh, Abhradeep Thakurta. 4599-4632 [doi]
• Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via RegressionAleksandrs Slivkins, Karthik Abinav Sankararaman, Dylan J. Foster. 4633-4656 [doi]
• Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational InferenceArnaud Descours, Tom Huix, Arnaud Guillin, Manon Michel, Éric Moulines, Boris Nectoux. 4657-4695 [doi]
• Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-OptimalMoïse Blanchard, Junhui Zhang, Patrick Jaillet. 4696-4736 [doi]
• Sparse PCA Beyond Covariance ThresholdingGleb Novikov. 4737-4776 [doi]
• Finite-Sample Symmetric Mean Estimation with Fisher Information RateShivam Gupta 0002, Jasper C. H. Lee, Eric Price 0001. 4777-4830 [doi]
• Fast Algorithms for a New Relaxation of Optimal TransportMoses Charikar, Beidi Chen, Christopher Ré, Erik Waingarten. 4831-4862 [doi]
• Generalization Guarantees via Algorithm-dependent Rademacher ComplexitySarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli. 4863-4880 [doi]
• Shortest Program Interpolation LearningNaren Sarayu Manoj, Nathan Srebro. 4881-4901 [doi]
• p-Regression in the Arbitrary Partition Model of CommunicationYi Li, Honghao Lin, David P. Woodruff. 4902-4928 [doi]
• On Classification-Calibration of Gamma-Phi LossesYutong Wang, Clayton Scott. 4929-4951 [doi]
• Asymptotically Optimal Generalization Error Bounds for Noisy, Iterative AlgorithmsIbrahim Issa, Amedeo Roberto Esposito, Michael Gastpar. 4952-4976 [doi]
• Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational EfficiencyHeyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu. 4977-5020 [doi]
• PAC Verification of Statistical AlgorithmsSaachi Mutreja, Jonathan Shafer. 5021-5043 [doi]
• Active Coverage for PAC Reinforcement LearningAymen Al Marjani, Andrea Tirinzoni, Emilie Kaufmann. 5044-5109 [doi]
• Ticketed Learning-Unlearning SchemesBadih Ghazi, Pritish Kamath, Ravi Kumar 0001, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang. 5110-5139 [doi]
• Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix SensingMahdi Soltanolkotabi, Dominik Stöger, Changzhi Xie. 5140-5142 [doi]
• U-Calibration: Forecasting for an Unknown AgentBobby Kleinberg, Renato Paes Leme, Jon Schneider, Yifeng Teng. 5143-5145 [doi]
• STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave GamesConstantinos Daskalakis, Noah Golowich, Stratis Skoulakis, Emmanouil Zampetakis. 5146-5198 [doi]
• Empirical Bayes via ERM and Rademacher complexities: the Poisson modelSoham Jana, Yury Polyanskiy, Anzo Z. Teh, Yihong Wu 0001. 5199-5235 [doi]
• Kernelized Diffusion MapsLoucas Pillaud-Vivien, Francis R. Bach. 5236-5259 [doi]
• Statistical and Computational Limits for Tensor-on-Tensor Association DetectionIlias Diakonikolas, Daniel M. Kane, Yuetian Luo, Anru Zhang. 5260-5310 [doi]
• Sparsity-aware generalization theory for deep neural networksRamchandran Muthukumar, Jeremias Sulam. 5311-5342 [doi]
• Is Planted Coloring Easier than Planted Clique?Pravesh Kothari, Santosh S. Vempala, Alexander S. Wein, Jeff Xu. 5343-5372 [doi]
• Moments, Random Walks, and Limits for Spectrum ApproximationYujia Jin, Christopher Musco, Aaron Sidford, Apoorv Vikram Singh. 5373-5394 [doi]
• Minimax optimal testing by classificationPatrik R. Gerber, Yanjun Han, Yury Polyanskiy. 5395-5432 [doi]
• Improper Multiclass BoostingNataly Brukhim, Steve Hanneke, Shay Moran. 5433-5452 [doi]
• Distribution-Independent Regression for Generalized Linear Models with Oblivious CorruptionsIlias Diakonikolas, Sushrut Karmalkar, Jong Ho Park, Christos Tzamos. 5453-5475 [doi]
• Sharper Model-free Reinforcement Learning for Average-reward Markov Decision ProcessesZihan Zhang, Qiaomin Xie. 5476-5477 [doi]
• The Aggregation-Heterogeneity Trade-off in Federated LearningXuyang Zhao, Huiyuan Wang, Wei Lin. 5478-5502 [doi]
• A Blackbox Approach to Best of Both Worlds in Bandits and BeyondChristoph Dann, Chen-Yu Wei, Julian Zimmert. 5503-5570 [doi]
• The Computational Complexity of Finding Stationary Points in Non-Convex OptimizationAlexandros Hollender, Emmanouil Zampetakis. 5571-5572 [doi]
• Sharp thresholds in inference of planted subgraphsElchanan Mossel, Jonathan Niles-Weed, Youngtak Sohn, Nike Sun, Ilias Zadik. 5573-5577 [doi]
• Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian DistributionsGavin Brown, Samuel Hopkins, Adam Smith. 5578-5579 [doi]
• Learning Narrow One-Hidden-Layer ReLU NetworksSitan Chen, Zehao Dou, Surbhi Goel, Adam R. Klivans, Raghu Meka. 5580-5614 [doi]
• Universal Rates for Multiclass LearningSteve Hanneke, Shay Moran, Qian Zhang. 5615-5681 [doi]
• Multiclass Online Learning and Uniform ConvergenceSteve Hanneke, Shay Moran, Vinod Raman, Unique Subedi, Ambuj Tewari. 5682-5696 [doi]
• Local Risk Bounds for Statistical AggregationJaouad Mourtada, Tomas Vaskevicius, Nikita Zhivotovskiy. 5697-5698 [doi]
• The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural NetworksYuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu. 5699-5753 [doi]
• On a Class of Gibbs Sampling over NetworksBo Yuan, JiaoJiao Fan, Jiaming Liang, Andre Wibisono, Yongxin Chen. 5754-5780 [doi]
• Limits of Model Selection under Transfer LearningSteve Hanneke, Samory Kpotufe, Yasaman Mahdaviyeh. 5781-5812 [doi]
• Bandit Learnability can be UndecidableSteve Hanneke, Liu Yang 0001. 5813-5849 [doi]
• Detection-Recovery and Detection-Refutation Gaps via Reductions from Planted CliqueGuy Bresler, Tianze Jiang. 5850-5889 [doi]
• Fine-Grained Distribution-Dependent Learning CurvesOlivier Bousquet, Steve Hanneke, Shay Moran, Jonathan Shafer, Ilya O. Tolstikhin. 5890-5924 [doi]
• Efficient median of means estimatorStanislav Minsker. 5925-5933 [doi]
• Open problem: log(n) factor in "Local Glivenko-CantelliDoron Cohen, Aryeh Kontorovich. 5934-5936 [doi]
• Open Problem: Learning sparse linear concepts by priming the featuresManfred K. Warmuth, Ehsan Amid. 5937-5942 [doi]
• Open Problem: The Sample Complexity of Multi-Distribution Learning for VC ClassesPranjal Awasthi, Nika Haghtalab, Eric Zhao 0003. 5943-5949 [doi]
• Open Problem: Polynomial linearly-convergent method for g-convex optimization?Christopher Criscitiello, David Martínez-Rubio, Nicolas Boumal. 5950-5956 [doi]
• Open Problem: Is There a First-Order Method that Only Converges to Local Minimax Optima?Jiseok Chae, Kyuwon Kim, Donghwan Kim. 5957-5964 [doi]