Table of Contents

• Preface1-3 [doi]
• When and why randomised exploration works (in linear bandits)Marc Abeille, David Janz, Ciara Pike-Burke. 4-22 [doi]
• Generalization bounds for mixing processes via delayed online-to-PAC conversionsBaptiste Abélès, Eugenio Clerico, Gergely Neu. 23-40 [doi]
• Agnostic Private Density Estimation for GMMs via List Global StabilityMohammad Afzali, Hassan Ashtiani, Christopher Liaw. 41-66 [doi]
• Refining the Sample Complexity of Comparative LearningSajad Ashkezari, Ruth Urner. 67-88 [doi]
• Understanding Aggregations of Proper Learners in Multiclass ClassificationJulian Asilis, Mikael Møller Høgsgaard, Grigoris Velegkas. 89-111 [doi]
• Proper Learnability and the Role of Unlabeled DataJulian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng. 112-133 [doi]
• Sample Compression Scheme ReductionsIdan Attias, Steve Hanneke, Arvind Ramaswami. 134-162 [doi]
• Strategyproof Learning with AdviceEric Balkanski, Cherlin Zhu. 163-166 [doi]
• Cost-Free Fairness in Online Correlation ClusteringEric Balkanski, Jason Chatzitheodorou, Andreas Maggiori. 167-203 [doi]
• Non-stochastic Bandits With Evolving ObservationsYogev Bar-On, Yishay Mansour. 204-227 [doi]
• Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits ProblemAvrim Blum, Kavya Ravichandran. 228-245 [doi]
• A Model for Combinatorial Dictionary Learning and InferenceAvrim Blum, Kavya Ravichandran. 246-288 [doi]
• Differentially Private Multi-Sampling from DistributionsAlbert Cheu, Debanuj Nayak. 289-314 [doi]
• Near-Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large BatchesChristopher A. Choquette-Choo, Arun Ganesh, Abhradeep Guha Thakurta. 315-348 [doi]
• Generalisation under gradient descent via deterministic PAC-BayesEugenio Clerico, Tyler Farghly, George Deligiannidis, Benjamin Guedj, Arnaud Doucet. 349-389 [doi]
• Boosting, Voting Classifiers and Randomized Sample Compression SchemesArthur da Cunha, Kasper Green Larsen, Martin Ritzert. 390-404 [doi]
• Effective Littlestone dimensionValentino Delle Rose, Alexander Kozachinskiy, Tomasz Steifer. 405-417 [doi]
• Is Transductive Learning Equivalent to PAC Learning?Shaddin Dughmi, Yusuf Hakan Kalayci, Grayson York. 418-443 [doi]
• Full Swap Regret and Discretized CalibrationMaxwell Fishelson, Robert Kleinberg, Princewill Okoroafor, Renato Paes Leme, Jon Schneider, Yifeng Teng. 444-480 [doi]
• A PAC-Bayesian Link Between Generalisation and Flat MinimaMaxime Haddouche, Paul Viallard, Umut Simsekli, Benjamin Guedj. 481-511 [doi]
• Reliable Active Apprenticeship LearningSteve Hanneke, Liu Yang 0001, Gongju Wang, Yulun Song. 512-538 [doi]
• For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are EquivalentSteve Hanneke, Amirreza Shaeiri, Hongao Wang. 539-559 [doi]
• A Complete Characterization of Learnability for Stochastic Noisy BanditsSteve Hanneke, Kun Wang. 560-577 [doi]
• Efficient Optimal PAC LearningMikael Møller Høgsgaard. 578-580 [doi]
• Do PAC-Learners Learn the Marginal Distribution?Max Hopkins, Daniel M. Kane, Shachar Lovett, Gaurav Mahajan. 581-610 [doi]
• Optimal and learned algorithms for the online list update problem with Zipfian accessesPiotr Indyk, Isabelle Quaye, Ronitt Rubinfeld, Sandeep Silwal. 611-648 [doi]
• Information-Theoretic Guarantees for Recovering Low-Rank Tensors from Symmetric Rank-One MeasurementsEren C. Kizildag. 649-652 [doi]
• Sharp bounds on aggregate expert errorAryeh Kontorovich, Ariel Avital. 653-663 [doi]
• Quantile Multi-Armed Bandits with 1-bit FeedbackIvan Lau, Jonathan Scarlett. 664-699 [doi]
• On the Hardness of Learning One Hidden Layer Neural NetworksShuchen Li, Ilias Zadik, Manolis Zampetakis. 700-701 [doi]
• Minimax-optimal and Locally-adaptive Online Nonparametric RegressionPaul Liautaud, Pierre Gaillard, Olivier Wintenberger. 702-735 [doi]
• Error dynamics of mini-batch gradient descent with random reshuffling for least squares regressionJackie Lok, Rishi Sonthalia, Elizaveta Rebrova. 736-770 [doi]
• Computationally efficient reductions between some statistical modelsMengqi Lou, Guy Bresler, Ashwin Pananjady. 771 [doi]
• Enhanced H-Consistency BoundsAnqi Mao, Mehryar Mohri, Yutao Zhong 0002. 772-813 [doi]
• Center-Based Approximation of a Drifting DistributionAlessio Mazzetto, Matteo Ceccarello, Andrea Pietracaprina, Geppino Pucci, Eli Upfal. 814-845 [doi]
• Fast Convergence of Φ-Divergence Along the Unadjusted Langevin Algorithm and Proximal SamplerSiddharth Mitra, Andre Wibisono. 846-869 [doi]
• A Characterization of List RegressionChirag Pabbaraju, Sahasrajit Sarmasarkar. 870-920 [doi]
• On Generalization Bounds for Neural Networks with Low Rank LayersAndrea Pinto, Akshay Rangamani, Tomaso A. Poggio. 921-936 [doi]
• Data Dependent Regret Bounds for Online Portfolio Selection with Predicted ReturnsSudeep Raja Putta, Shipra Agrawal 0001. 937-984 [doi]
• A Unified Theory of Supervised Online LearnabilityVinod Raman, Unique Subedi, Ambuj Tewari. 985-1007 [doi]
• An Online Feasible Point Method for Benign Generalized Nash Equilibrium ProblemsSarah Sachs, Hédi Hadiji, Tim van Erven, Mathias Staudigl. 1008-1040 [doi]
• The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex OptimizationMatan Schliserman, Uri Sherman, Tomer Koren. 1041-1107 [doi]
• Efficient PAC Learning of Halfspaces with Constant Malicious Noise RateJie Shen. 1108-1137 [doi]
• Self-Directed Node Classification on GraphsGeorgy Sokolov, Maximilian Thiessen, Margarita Akhmejanova, Fabio Vitale, Francesco Orabona. 1138-1168 [doi]
• High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin AlgorithmVishwak Srinivasan, Andre Wibisono, Ashia Wilson. 1169-1220 [doi]
• Clustering with bandit feedback: breaking down the computation/information gapVictor Thuot, Alexandra Carpentier, Christophe Giraud 0002, Nicolas Verzelen. 1221-1284 [doi]
• Online Learning of Quantum States with Logarithmic Loss via VB-FTRLWei-Fu Tseng, Kai-Chun Chen, Zi-Hong Xiao, Yen-Huan Li. 1285-1312 [doi]
• Noisy Computing of the Threshold FunctionZiao Wang, Nadim Ghaddar, Banghua Zhu, Lele Wang 0001. 1313-1315 [doi]
• How rotation invariant algorithms are fooled by noise on sparse targetsManfred K. Warmuth, Wojciech Kotlowski, Matt Jones 0002, Ehsan Amid. 1316-1360 [doi]
• Logarithmic Regret for Unconstrained Submodular Maximization Stochastic BanditJulien Zhou, Pierre Gaillard, Thibaud Rahier, Julyan Arbel. 1361-1385 [doi]
• The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity AnalysisMatthew Zurek, Yudong Chen 0001. 1386-1387 [doi]