Table of Contents

• Algorithmic Learning Theory 2021: Preface1-2 [doi]
• Last-Iterate Convergence Rates for Min-Max Optimization: Convergence of Hamiltonian Gradient Descent and Consensus OptimizationJacob D. Abernethy, Kevin A. Lai, Andre Wibisono. 3-47 [doi]
• Differentially Private Assouad, Fano, and Le CamJayadev Acharya, Ziteng Sun, Huanyu Zhang. 48-78 [doi]
• Estimating Sparse Discrete Distributions Under Privacy and Communication ConstraintsJayadev Acharya, Peter Kairouz, Yuhan Liu, Ziteng Sun. 79-98 [doi]
• Efficient Algorithms for Stochastic Repeated Second-price AuctionsJuliette Achddou, Olivier Cappé, Aurélien Garivier. 99-150 [doi]
• Intervention Efficient Algorithms for Approximate Learning of Causal GraphsRaghavendra Addanki, Andrew McGregor, Cameron Musco. 151-184 [doi]
• On the Sample Complexity of Privately Learning Unbounded High-Dimensional GaussiansIshaq Aden-Ali, Hassan Ashtiani, Gautam Kamath 0001. 185-216 [doi]
• Stochastic Dueling Bandits with Adversarial CorruptionArpit Agarwal, Shivani Agarwal 0001, Prathamesh Patil. 217-248 [doi]
• A Deep Conditioning Treatment of Neural NetworksNaman Agarwal, Pranjal Awasthi, Satyen Kale. 249-305 [doi]
• Stochastic Top-K Subset Bandits with Linear Space and Non-Linear FeedbackMridul Agarwal, Vaneet Aggarwal, Christopher J. Quinn, Abhishek K. Umrawal. 306-339 [doi]
• Sequential prediction under log-loss with side informationAlankrita Bhatt, Young-Han Kim 0001. 340-344 [doi]
• No-substitution k-means Clustering with Adversarial OrderRobi Bhattacharjee, Michal Moshkovitz. 345-366 [doi]
• Testing Product Distributions: A Closer LookArnab Bhattacharyya 0001, Sutanu Gayen, Saravanan Kandasamy 0002, N. V. Vinodchandran. 367-396 [doi]
• Online Boosting with Bandit FeedbackNataly Brukhim, Elad Hazan. 397-420 [doi]
• Bounding, Concentrating, and Truncating: Unifying Privacy Loss Composition for Data AnalyticsMark Cesar, Ryan Rogers 0002. 421-457 [doi]
• Learning and Testing Irreducible Markov Chains via the k-Cover TimeSiu On Chan, Qinghua Ding, Sing Hei Li. 458-480 [doi]
• Learning a mixture of two subspaces over finite fieldsAidao Chen, Anindya De, Aravindan Vijayaraghavan. 481-504 [doi]
• Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial TimeThibaut Cuvelier, Richard Combes, Eric Gourdin. 505-528 [doi]
• An Efficient Algorithm for Cooperative Semi-BanditsRiccardo Della Vecchia, Tommaso Cesari. 529-552 [doi]
• Last Round Convergence and No-Dynamic Regret in Asymmetric Repeated GamesLe Cong Dinh, Tri-Dung Nguyen, Alain B. Zemkoho, Long Tran-Thanh. 553-577 [doi]
• Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds RevisitedOmar Darwiche Domingues, Pierre Ménard, Emilie Kaufmann, Michal Valko. 578-598 [doi]
• Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret BoundsEhsan Emamjomeh-Zadeh, Chen-Yu Wei, Haipeng Luo, David Kempe 0001. 599-618 [doi]
• A Technical Note on Non-Stationary Parametric Bandits: Existing Mistakes and Preliminary SolutionsLouis Faury, Yoan Russac, Marc Abeille, Clément Calauzènes. 619-626 [doi]
• Subspace Embeddings under Nonlinear TransformationsAarshvi Gajjar, Cameron Musco. 656-672 [doi]
• Efficient sampling from the Bingham distributionRong Ge 0001, Holden Lee, Jianfeng Lu 0001, Andrej Risteski. 673-685 [doi]
• Near-tight closure b ounds for the Littlestone and threshold dimensionsBadih Ghazi, Noah Golowich, Ravi Kumar 0001, Pasin Manurangsi. 686-696 [doi]
• Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin BoundSteve Hanneke, Aryeh Kontorovich. 697-721 [doi]
• Submodular combinatorial information measures with applications in machine learningRishabh K. Iyer, Ninad Khargoankar, Jeff A. Bilmes, Himanshu Asanani. 722-754 [doi]
• Precise Minimax Regret for Logistic Regression with Categorical Feature ValuesPhilippe Jacquet, Gil I. Shamir, Wojciech Szpankowski. 755-771 [doi]
• Characterizing the implicit bias via a primal-dual analysisZiwei Ji, Matus Telgarsky. 772-804 [doi]
• Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit FeedbackMarc Jourdan, Mojmír Mutný, Johannes Kirschner, Andreas Krause 0001. 805-849 [doi]
• Efficient Learning with Arbitrary Covariate ShiftAdam Tauman Kalai, Varun Kanade. 850-864 [doi]
• Adaptive Reward-Free ExplorationEmilie Kaufmann, Pierre Ménard, Omar Darwiche Domingues, Anders Jonsson, Edouard Leurent, Michal Valko. 865-891 [doi]
• Unexpected Effects of Online no-Substitution k-means ClusteringMichal Moshkovitz. 892-930 [doi]
• Descent-to-Delete: Gradient-Based Methods for Machine UnlearningSeth Neel, Aaron Roth 0001, Saeed Sharifi-Malvajerdi. 931-962 [doi]
• Uncertainty quantification using martingales for misspecified Gaussian processesWillie Neiswanger, Aaditya Ramdas. 963-982 [doi]
• Learning with Comparison Feedback: Online Estimation of Sample StatisticsMichela Meister, Sloan Nietert. 983-1001 [doi]
• Online Learning of Facility LocationsStephen Pasteris, Ting He 0001, Fabio Vitale, Shiqiang Wang 0001, Mark Herbster. 1002-1050 [doi]
• Statistical guarantees for generative models without dominationNicolas Schreuder, Victor-Emmanuel Brunel, Arnak S. Dalalyan. 1051-1071 [doi]
• Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise ToleranceJie Shen 0005, Chicheng Zhang. 1072-1113 [doi]
• Self-Tuning Bandits over Unknown Covariate-ShiftsJoseph Suk, Samory Kpotufe. 1114-1156 [doi]
• Sample Complexity Bounds for Stochastic Shortest Path with a Generative ModelJean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric. 1157-1178 [doi]
• Contrastive learning, multi-view redundancy, and linear modelsChristopher Tosh, Akshay Krishnamurthy, Daniel Hsu 0001. 1179-1206 [doi]
• Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled DataDi Wang, Huangyu Zhang, Marco Gaboardi, Jinhui Xu 0001. 1207-1213 [doi]
• A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layerManfred K. Warmuth, Wojciech Kotlowski, Ehsan Amid. 1214-1236 [doi]
• Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value FunctionsGellért Weisz, Philip Amortila, Csaba Szepesvári. 1237-1264 [doi]
• Non-uniform Consistency of Online Learning with Random SamplingChanglong Wu, Narayana Santhanam. 1265-1285 [doi]