Table of Contents

• Conference on Learning Theory 2020: PrefaceJacob D. Abernethy, Shivani Agarwal 0001. 1-2 [doi]
• Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-FitJayadev Acharya, Clément L. Canonne, Yanjun Han, Ziteng Sun, Himanshu Tyagi. 3-40 [doi]
• Distributed Signal Detection under Communication ConstraintsJayadev Acharya, Clément L. Canonne, Himanshu Tyagi. 41-63 [doi]
• Optimality and Approximation with Policy Gradient Methods in Markov Decision ProcessesAlekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan. 64-66 [doi]
• Model-Based Reinforcement Learning with a Generative Model is Minimax OptimalAlekh Agarwal, Sham M. Kakade, Lin F. Yang. 67-83 [doi]
• From Nesterov's Estimate Sequence to Riemannian AccelerationKwangjun Ahn, Suvrit Sra. 84-118 [doi]
• Closure Properties for Private Classification and Online PredictionNoga Alon, Amos Beimel, Shay Moran, Uri Stemmer. 119-152 [doi]
• Hierarchical Clustering: A 0.585 Revenue ApproximationNoga Alon, Yossi Azar, Danny Vainstein. 153-162 [doi]
• Winnowing with Gradient DescentEhsan Amid, Manfred K. Warmuth. 163-182 [doi]
• Pan-Private Uniformity TestingKareem Amin, Matthew Joseph, Jieming Mao. 183-218 [doi]
• Dimension-Free Bounds for Chasing Convex FunctionsC. J. Argue, Anupam Gupta, Guru Guruganesh. 219-241 [doi]
• Second-Order Information in Non-Convex Stochastic Optimization: Power and LimitationsYossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan. 242-299 [doi]
• Data-driven confidence bands for distributed nonparametric regressionValeriy Avanesov. 300-322 [doi]
• Estimating Principal Components under Adversarial PerturbationsPranjal Awasthi, Xue Chen 0001, Aravindan Vijayaraghavan. 323-362 [doi]
• Active Local LearningArturs Backurs, Avrim Blum, Neha Gupta. 363-390 [doi]
• Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-AscentJames P. Bailey, Gauthier Gidel, Georgios Piliouras. 391-407 [doi]
• Calibrated Surrogate Losses for Adversarially Robust ClassificationHan Bao, Clayton Scott, Masashi Sugiyama. 408-451 [doi]
• Complexity Guarantees for Polyak Steps with MomentumMathieu Barré, Adrien Taylor, Alexandre d'Aspremont. 452-478 [doi]
• Free Energy Wells and Overlap Gap Property in Sparse PCAGérard Ben Arous, Alexander S. Wein, Ilias Zadik. 479-482 [doi]
• Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like processGuy Blanc, Neha Gupta, Gregory Valiant, Paul Valiant. 483-513 [doi]
• Hardness of Identity Testing for Restricted Boltzmann Machines and Potts modelsAntonio Blanca, Zongchen Chen, Daniel Stefankovic, Eric Vigoda. 514-529 [doi]
• Selfish Robustness and Equilibria in Multi-Player BanditsEtienne Boursier, Vianney Perchet. 530-581 [doi]
• Proper Learning, Helly Number, and an Optimal SVM BoundOlivier Bousquet, Steve Hanneke, Shay Moran, Nikita Zhivotovskiy. 582-609 [doi]
• Sharper Bounds for Uniformly Stable AlgorithmsOlivier Bousquet, Yegor Klochkov, Nikita Zhivotovskiy. 610-626 [doi]
• The Gradient Complexity of Linear RegressionMark Braverman, Elad Hazan, Max Simchowitz, Blake E. Woodworth. 627-647 [doi]
• Reducibility and Statistical-Computational Gaps from Secret LeakageMatthew Brennan, Guy Bresler. 648-847 [doi]
• A Corrective View of Neural Networks: Representation, Memorization and LearningGuy Bresler, Dheeraj Nagaraj. 848-901 [doi]
• ID3 Learns Juntas for Smoothed Product DistributionsAlon Brutzkus, Amit Daniely, Eran Malach. 902-915 [doi]
• Coordination without communication: optimal regret in two players multi-armed banditsSébastien Bubeck, Thomas Budzinski. 916-939 [doi]
• How to Trap a Gradient FlowSébastien Bubeck, Dan Mikulincer. 940-960 [doi]
• Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear WithoutSébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke. 961-987 [doi]
• Highly smooth minimization of non-smooth problemsBrian Bullins. 988-1030 [doi]
• Efficient, Noise-Tolerant, and Private Learning via BoostingMark Bun, Marco Leandro Carmosino, Jessica Sorrell. 1031-1077 [doi]
• The estimation error of general first order methodsMichael Celentano, Andrea Montanari, Yuchen Wu. 1078-1141 [doi]
• Bounds in query learningHunter Chase, James Freitag. 1142-1160 [doi]
• Learning Polynomials in Few Relevant DimensionsSitan Chen, Raghu Meka. 1161-1227 [doi]
• The Influence of Shape Constraints on the Thresholding Bandit ProblemJames Cheshire, Pierre Ménard, Alexandra Carpentier. 1228-1275 [doi]
• Gradient descent algorithms for Bures-Wasserstein barycentersSinho Chewi, Tyler Maunu, Philippe Rigollet, Austin J. Stromme. 1276-1304 [doi]
• Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic LossLénaïc Chizat, Francis Bach. 1305-1338 [doi]
• ODE-Inspired Analysis for the Biological Version of Oja's Rule in Solving Streaming PCAChi-Ning Chou, Mien Brabeeba Wang. 1339-1343 [doi]
• Pessimism About Unknown Unknowns Inspires ConservatismMichael K. Cohen, Marcus Hutter. 1344-1373 [doi]
• Optimal Group TestingAmin Coja-Oghlan, Oliver Gebhard, Max Hahn-Klimroth, Philipp Loick. 1374-1388 [doi]
• PAC learning with stable and private predictionsYuval Dagan, Vitaly Feldman. 1389-1410 [doi]
• High probability guarantees for stochastic convex optimizationDamek Davis, Dmitriy Drusvyatskiy. 1411-1427 [doi]
• Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational InequalitiesJelena Diakonikolas. 1428-1451 [doi]
• Approximation Schemes for ReLU RegressionIlias Diakonikolas, Surbhi Goel, Sushrut Karmalkar, Adam R. Klivans, Mahdi Soltanolkotabi. 1452-1485 [doi]
• Learning Halfspaces with Massart Noise Under Structured DistributionsIlias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis. 1486-1513 [doi]
• Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU NetworksIlias Diakonikolas, Daniel M. Kane, Vasilis Kontonis, Nikos Zarifis. 1514-1539 [doi]
• Consistent recovery threshold of hidden nearest neighbor graphsJian Ding, Yihong Wu 0001, Jiaming Xu, Dana Yang. 1540-1553 [doi]
• Root-n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman RankKefan Dong, Jian Peng 0001, Yining Wang, Yuan Zhou 0007. 1554-1557 [doi]
• Embedding Dimension of Polyhedral LossesJessie Finocchiaro, Rafael M. Frongillo, Bo Waggoner. 1558-1585 [doi]
• Efficient Parameter Estimation of Truncated Boolean Product DistributionsDimitris Fotakis, Alkis Kalavasis, Christos Tzamos. 1586-1600 [doi]
• Rigorous Guarantees for Tyler's M-Estimator via Quantum ExpansionWilliam Cole Franks, Ankur Moitra. 1601-1632 [doi]
• From tree matching to sparse graph alignmentLuca Ganassali, Laurent Massoulié. 1633-1665 [doi]
• On the Convergence of Stochastic Gradient Descent with Low-Rank Projections for Convex Low-Rank Matrix ProblemsDan Garber. 1666-1681 [doi]
• Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian MatricesCédric Gerbelot, Alia Abbara, Florent Krzakala. 1682-1713 [doi]
• No-Regret Prediction in Marginally Stable SystemsUdaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang. 1714-1757 [doi]
• Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point ProblemsNoah Golowich, Sarath Pattathil, Constantinos Daskalakis, Asuman E. Ozdaglar. 1758-1784 [doi]
• Locally Private Hypothesis SelectionSivakanth Gopi, Gautam Kamath 0001, Janardhan Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang. 1785-1816 [doi]
• Bessel Smoothing and Multi-Distribution Property EstimationYi Hao, Ping Li. 1817-1876 [doi]
• Faster Projection-free Online LearningElad Hazan, Edgar Minasyan. 1877-1893 [doi]
• Near-Optimal Methods for Minimizing Star-Convex Functions and BeyondOliver Hinder, Aaron Sidford, Nimit Sharad Sohoni. 1894-1938 [doi]
• A Greedy Anytime Algorithm for Sparse PCAGuy Holtzman, Adam Soffer, Dan Vilenchik. 1939-1956 [doi]
• Noise-tolerant, Reliable Active Classification with Comparison QueriesMax Hopkins, Daniel Kane, Shachar Lovett, Gaurav Mahajan. 1957-2006 [doi]
• Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret RegimesYichun Hu, Nathan Kallus, Xiaojie Mao. 2007-2010 [doi]
• Extrapolating the profile of a finite populationSoham Jana, Yury Polyanskiy, Yihong Wu 0001. 2011-2033 [doi]
• Precise Tradeoffs in Adversarial Training for Linear RegressionAdel Javanmard, Mahdi Soltanolkotabi, Hamed Hassani. 2034-2078 [doi]
• Robust causal inference under covariate shift via worst-case subpopulation treatment effectsSookyo Jeong, Hongseok Namkoong. 2079-2084 [doi]
• Efficient improper learning for online logistic regressionRémi Jézéquel, Pierre Gaillard, Alessandro Rudi. 2085-2108 [doi]
• Gradient descent follows the regularization path for general lossesZiwei Ji, Miroslav Dudík, Robert E. Schapire, Matus Telgarsky. 2109-2136 [doi]
• Provably efficient reinforcement learning with linear function approximationChi Jin, Zhuoran Yang, Zhaoran Wang, Michael I. Jordan. 2137-2143 [doi]
• Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian NoiseMaxim Kaledin, Eric Moulines, Alexey Naumov, Vladislav Tadic, Hoi-To Wai. 2144-2203 [doi]
• Private Mean Estimation of Heavy-Tailed DistributionsGautam Kamath 0001, Vikrant Singhal, Jonathan Ullman. 2204-2235 [doi]
• Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin ComplexityPritish Kamath, Omar Montasser, Nathan Srebro. 2236-2262 [doi]
• Privately Learning Thresholds: Closing the Exponential GapHaim Kaplan, Katrina Ligett, Yishay Mansour, Moni Naor, Uri Stemmer. 2263-2285 [doi]
• Online Learning with Vector Costs and Bandits with KnapsacksThomas Kesselheim, Sahil Singla 0001. 2286-2305 [doi]
• Universal Approximation with Deep Narrow NetworksPatrick Kidger, Terry J. Lyons. 2306-2327 [doi]
• Information Directed Sampling for Linear Partial MonitoringJohannes Kirschner, Tor Lattimore, Andreas Krause 0001. 2328-2369 [doi]
• New Potential-Based Bounds for Prediction with Expert AdviceVladimir A. Kobzar, Robert V. Kohn, Zhilei Wang. 2370-2405 [doi]
• On Suboptimality of Least Squares with Application to Estimation of Convex BodiesGil Kur, Alexander Rakhlin, Adityanand Guntuboyina. 2406-2424 [doi]
• The EM Algorithm gives Sample-Optimality for Learning Mixtures of Well-Separated GaussiansJeongyeol Kwon, Constantine Caramanis. 2425-2487 [doi]
• Exploration by Optimisation in Partial MonitoringTor Lattimore, Csaba Szespvári. 2488-2515 [doi]
• A Closer Look at Small-loss Bounds for Bandits with Graph FeedbackChung-wei Lee, Haipeng Luo, Mengxiao Zhang. 2516-2564 [doi]
• Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte CarloYin Tat Lee, Ruoqi Shen, Kevin Tian. 2565-2597 [doi]
• A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian RatesZhixian Lei, Kyle Luh, Prayaag Venkat, Fred Zhang. 2598-2612 [doi]
• Learning Over-Parametrized Two-Layer Neural Networks beyond NTKYuanzhi Li, Tengyu Ma, Hongyang R. Zhang. 2613-2682 [doi]
• On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of KernelsTengyuan Liang, Alexander Rakhlin, Xiyu Zhai. 2683-2711 [doi]
• Learning Entangled Single-Sample Gaussians in the Subset-of-Signals ModelYingyu Liang, Hui Yuan. 2712-2737 [doi]
• Near-Optimal Algorithms for Minimax OptimizationTianyi Lin, Chi Jin, Michael I. Jordan. 2738-2779 [doi]
• Better Algorithms for Estimating Non-Parametric Models in Crowd-Sourcing and Rank AggregationAllen Liu, Ankur Moitra. 2780-2829 [doi]
• Tight Lower Bounds for Combinatorial Multi-Armed BanditsNadav Merlis, Shie Mannor. 2830-2857 [doi]
• Lipschitz and Comparator-Norm Adaptivity in Online LearningZakaria Mhammedi, Wouter M. Koolen. 2858-2887 [doi]
• Information Theoretic Optimal Learning of Gaussian Graphical ModelsSidhant Misra, Marc Vuffray, Andrey Y. Lokhov. 2888-2909 [doi]
• Parallels Between Phase Transitions and Circuit Complexity?Ankur Moitra, Elchanan Mossel, Colin Sandon. 2910-2946 [doi]
• On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic ConcentrationWenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan. 2947-2997 [doi]
• Extending Learnability to Auxiliary-Input Cryptographic Primitives and Meta-PAC LearningMikito Nanashima. 2998-3029 [doi]
• Fast Rates for Online Prediction with AbstentionGergely Neu, Nikita Zhivotovskiy. 3030-3048 [doi]
• Efficient and robust algorithms for adversarial linear contextual banditsGergely Neu, Julia Olkhovskaya. 3049-3068 [doi]
• An $\widetilde\mathcalO(m/\varepsilon^3.5)$-Cost Algorithm for Semidefinite Programs with Diagonal ConstraintsYin Tat Lee, Swati Padmanabhan. 3069-3119 [doi]
• Costly Zero Order OraclesRenato Paes Leme, Jon Schneider. 3120-3132 [doi]
• Adaptive Submodular Maximization under Stochastic Item CostsSrinivasan Parthasarathy 0002. 3133-3151 [doi]
• Covariance-adapting algorithm for semi-bandits with application to sparse outcomesPierre Perrault, Michal Valko, Vianney Perchet. 3152-3184 [doi]
• Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-LearningGuannan Qu, Adam Wierman. 3185-3205 [doi]
• List Decodable Subspace RecoveryPrasad Raghavendra, Morris Yau. 3206-3226 [doi]
• Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed BanditsChloé Rouyer, Yevgeny Seldin. 3227-3249 [doi]
• How Good is SGD with Random Shuffling?Itay Safran, Ohad Shamir. 3250-3284 [doi]
• A Nearly Optimal Variant of the Perceptron Algorithm for the Uniform Distribution on the Unit SphereMarco Schmalhofer. 3285-3295 [doi]
• Logistic Regression Regret: What's the Catch?Gil I. Shamir. 3296-3319 [doi]
• Improper Learning for Non-Stochastic ControlMax Simchowitz, Karan Singh, Elad Hazan. 3320-3436 [doi]
• Reasoning About Generalization via Conditional Mutual InformationThomas Steinke, Lydia Zakynthinou. 3437-3452 [doi]
• Estimation and Inference with Trees and Forests in High DimensionsVasilis Syrgkanis, Manolis Zampetakis. 3453-3454 [doi]
• Balancing Gaussian vectors in high dimensionPaxton Turner, Raghu Meka, Philippe Rigollet. 3455-3486 [doi]
• Active Learning for Identification of Linear Dynamical SystemsAndrew Wagenmaker, Kevin Jamieson. 3487-3582 [doi]
• Taking a hint: How to leverage loss predictors in contextual bandits?Chen-Yu Wei, Haipeng Luo, Alekh Agarwal. 3583-3634 [doi]
• Kernel and Rich Regimes in Overparametrized ModelsBlake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro. 3635-3673 [doi]
• Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated EquilibriumQiaomin Xie, Yudong Chen, Zhaoran Wang, Zhuoran Yang. 3674-3682 [doi]
• Tree-projected gradient descent for estimating gradient-sparse parameters on graphsSheng Xu, Zhou Fan, Sahand Negahban. 3683-3708 [doi]
• Non-asymptotic Analysis for Nonparametric TestingYun Yang, Zuofeng Shang, Guang Cheng. 3709-3755 [doi]
• Learning a Single Neuron with Gradient MethodsGilad Yehudai, Ohad Shamir. 3756-3786 [doi]
• Nearly Non-Expansive Bounds for Mahalanobis Hard ThresholdingXiao-Tong Yuan, Ping Li 0001. 3787-3813 [doi]
• Wasserstein Control of Mirror Langevin Monte CarloKelvin Shuangjian Zhang, Gabriel Peyré, Jalal Fadili, Marcelo Pereyra. 3814-3841 [doi]
• Open Problem: Model Selection for Contextual BanditsDylan J. Foster, Akshay Krishnamurthy, Haipeng Luo. 3842-3846 [doi]
• Open Problem: Tight Convergence of SGD in Constant DimensionTomer Koren, Shahar Segal. 3847-3851 [doi]
• Open Problem: Average-Case Hardness of Hypergraphic Planted Clique DetectionYuetian Luo, Anru R. Zhang. 3852-3856 [doi]
• Open Problem: Information Complexity of VC LearningThomas Steinke, Lydia Zakynthinou. 3857-3863 [doi]
• Open Problem: Fast and Optimal Online Portfolio SelectionTim van Erven, Dirk van der Hoeven, Wojciech Kotlowski, Wouter M. Koolen. 3864-3869 [doi]