![](https://dblp.org/img/logo.ua.320x120.png)
![](https://dblp.org/img/dropdown.dark.16x16.png)
![](https://dblp.org/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp.org/img/search.dark.16x16.png)
![search dblp](https://dblp.org/img/search.dark.16x16.png)
default search action
33rd COLT 2020: Virtual Event [Graz, Austria]
- Jacob D. Abernethy, Shivani Agarwal:
Conference on Learning Theory, COLT 2020, 9-12 July 2020, Virtual Event [Graz, Austria]. Proceedings of Machine Learning Research 125, PMLR 2020 - Jacob D. Abernethy, Shivani Agarwal:
Conference on Learning Theory 2020: Preface. 1-2 - Jayadev Acharya, Clément L. Canonne, Yanjun Han, Ziteng Sun, Himanshu Tyagi:
Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-Fit. 3-40 - Jayadev Acharya, Clément L. Canonne
, Himanshu Tyagi:
Distributed Signal Detection under Communication Constraints. 41-63 - Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan:
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. 64-66 - Alekh Agarwal, Sham M. Kakade, Lin F. Yang
:
Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal. 67-83 - Kwangjun Ahn, Suvrit Sra:
From Nesterov's Estimate Sequence to Riemannian Acceleration. 84-118 - Noga Alon, Amos Beimel, Shay Moran, Uri Stemmer:
Closure Properties for Private Classification and Online Prediction. 119-152 - Noga Alon, Yossi Azar, Danny Vainstein:
Hierarchical Clustering: A 0.585 Revenue Approximation. 153-162 - Ehsan Amid, Manfred K. Warmuth:
Winnowing with Gradient Descent. 163-182 - Kareem Amin, Matthew Joseph, Jieming Mao:
Pan-Private Uniformity Testing. 183-218 - C. J. Argue, Anupam Gupta, Guru Guruganesh:
Dimension-Free Bounds for Chasing Convex Functions. 219-241 - Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan:
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations. 242-299 - Valeriy Avanesov:
Data-driven confidence bands for distributed nonparametric regression. 300-322 - Pranjal Awasthi, Xue Chen, Aravindan Vijayaraghavan:
Estimating Principal Components under Adversarial Perturbations. 323-362 - Arturs Backurs, Avrim Blum, Neha Gupta:
Active Local Learning. 363-390 - James P. Bailey, Gauthier Gidel, Georgios Piliouras:
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent. 391-407 - Han Bao, Clayton Scott, Masashi Sugiyama:
Calibrated Surrogate Losses for Adversarially Robust Classification. 408-451 - Mathieu Barré, Adrien B. Taylor, Alexandre d'Aspremont:
Complexity Guarantees for Polyak Steps with Momentum. 452-478 - Gérard Ben Arous, Alexander S. Wein, Ilias Zadik:
Free Energy Wells and Overlap Gap Property in Sparse PCA. 479-482 - Guy Blanc, Neha Gupta, Gregory Valiant, Paul Valiant:
Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process. 483-513 - Antonio Blanca, Zongchen Chen, Daniel Stefankovic, Eric Vigoda:
Hardness of Identity Testing for Restricted Boltzmann Machines and Potts models. 514-529 - Etienne Boursier, Vianney Perchet:
Selfish Robustness and Equilibria in Multi-Player Bandits. 530-581 - Olivier Bousquet, Steve Hanneke, Shay Moran, Nikita Zhivotovskiy:
Proper Learning, Helly Number, and an Optimal SVM Bound. 582-609 - Olivier Bousquet, Yegor Klochkov, Nikita Zhivotovskiy:
Sharper Bounds for Uniformly Stable Algorithms. 610-626 - Mark Braverman, Elad Hazan, Max Simchowitz, Blake E. Woodworth:
The Gradient Complexity of Linear Regression. 627-647 - Matthew S. Brennan, Guy Bresler:
Reducibility and Statistical-Computational Gaps from Secret Leakage. 648-847 - Guy Bresler, Dheeraj Nagaraj:
A Corrective View of Neural Networks: Representation, Memorization and Learning. 848-901 - Alon Brutzkus, Amit Daniely, Eran Malach:
ID3 Learns Juntas for Smoothed Product Distributions. 902-915 - Sébastien Bubeck, Thomas Budzinski:
Coordination without communication: optimal regret in two players multi-armed bandits. 916-939 - Sébastien Bubeck, Dan Mikulincer:
How to Trap a Gradient Flow. 940-960 - Sébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke:
Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without. 961-987 - Brian Bullins:
Highly smooth minimization of non-smooth problems. 988-1030 - Mark Bun, Marco Leandro Carmosino, Jessica Sorrell:
Efficient, Noise-Tolerant, and Private Learning via Boosting. 1031-1077 - Michael Celentano, Andrea Montanari, Yuchen Wu:
The estimation error of general first order methods. 1078-1141 - Hunter Chase, James Freitag:
Bounds in query learning. 1142-1160 - Sitan Chen, Raghu Meka:
Learning Polynomials in Few Relevant Dimensions. 1161-1227 - James Cheshire, Pierre Ménard, Alexandra Carpentier:
The Influence of Shape Constraints on the Thresholding Bandit Problem. 1228-1275 - Sinho Chewi, Tyler Maunu, Philippe Rigollet, Austin J. Stromme:
Gradient descent algorithms for Bures-Wasserstein barycenters. 1276-1304 - Lénaïc Chizat, Francis R. Bach:
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss. 1305-1338 - Chi-Ning Chou, Mien Brabeeba Wang:
ODE-Inspired Analysis for the Biological Version of Oja's Rule in Solving Streaming PCA. 1339-1343 - Michael K. Cohen, Marcus Hutter:
Pessimism About Unknown Unknowns Inspires Conservatism. 1344-1373 - Amin Coja-Oghlan, Oliver Gebhard, Max Hahn-Klimroth, Philipp Loick:
Optimal Group Testing. 1374-1388 - Yuval Dagan, Vitaly Feldman:
PAC learning with stable and private predictions. 1389-1410 - Damek Davis, Dmitriy Drusvyatskiy:
High probability guarantees for stochastic convex optimization. 1411-1427 - Jelena Diakonikolas:
Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational Inequalities. 1428-1451 - Ilias Diakonikolas, Surbhi Goel, Sushrut Karmalkar, Adam R. Klivans, Mahdi Soltanolkotabi
:
Approximation Schemes for ReLU Regression. 1452-1485 - Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis:
Learning Halfspaces with Massart Noise Under Structured Distributions. 1486-1513 - Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis, Nikos Zarifis:
Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks. 1514-1539 - Jian Ding, Yihong Wu, Jiaming Xu, Dana Yang:
Consistent recovery threshold of hidden nearest neighbor graphs. 1540-1553 - Kefan Dong, Jian Peng, Yining Wang, Yuan Zhou:
Root-n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank. 1554-1557 - Jessie Finocchiaro, Rafael M. Frongillo, Bo Waggoner:
Embedding Dimension of Polyhedral Losses. 1558-1585 - Dimitris Fotakis, Alkis Kalavasis, Christos Tzamos:
Efficient Parameter Estimation of Truncated Boolean Product Distributions. 1586-1600 - William Cole Franks, Ankur Moitra:
Rigorous Guarantees for Tyler's M-Estimator via Quantum Expansion. 1601-1632 - Luca Ganassali, Laurent Massoulié:
From tree matching to sparse graph alignment. 1633-1665 - Dan Garber:
On the Convergence of Stochastic Gradient Descent with Low-Rank Projections for Convex Low-Rank Matrix Problems. 1666-1681 - Cédric Gerbelot, Alia Abbara, Florent Krzakala
:
Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices. 1682-1713 - Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang:
No-Regret Prediction in Marginally Stable Systems. 1714-1757 - Noah Golowich, Sarath Pattathil, Constantinos Daskalakis, Asuman E. Ozdaglar:
Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems. 1758-1784 - Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang:
Locally Private Hypothesis Selection. 1785-1816 - Yi Hao, Ping Li:
Bessel Smoothing and Multi-Distribution Property Estimation. 1817-1876 - Elad Hazan, Edgar Minasyan:
Faster Projection-free Online Learning. 1877-1893 - Oliver Hinder, Aaron Sidford, Nimit Sharad Sohoni:
Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond. 1894-1938 - Guy Holtzman, Adam Soffer, Dan Vilenchik:
A Greedy Anytime Algorithm for Sparse PCA. 1939-1956 - Max Hopkins, Daniel Kane, Shachar Lovett, Gaurav Mahajan:
Noise-tolerant, Reliable Active Classification with Comparison Queries. 1957-2006 - Yichun Hu, Nathan Kallus, Xiaojie Mao:
Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes. 2007-2010 - Soham Jana, Yury Polyanskiy, Yihong Wu:
Extrapolating the profile of a finite population. 2011-2033 - Adel Javanmard, Mahdi Soltanolkotabi
, Hamed Hassani:
Precise Tradeoffs in Adversarial Training for Linear Regression. 2034-2078 - Sookyo Jeong, Hongseok Namkoong:
Robust causal inference under covariate shift via worst-case subpopulation treatment effects. 2079-2084 - Rémi Jézéquel, Pierre Gaillard, Alessandro Rudi:
Efficient improper learning for online logistic regression. 2085-2108 - Ziwei Ji, Miroslav Dudík, Robert E. Schapire, Matus Telgarsky:
Gradient descent follows the regularization path for general losses. 2109-2136 - Chi Jin
, Zhuoran Yang, Zhaoran Wang, Michael I. Jordan:
Provably efficient reinforcement learning with linear function approximation. 2137-2143 - Maxim Kaledin, Eric Moulines, Alexey Naumov, Vladislav Tadic, Hoi-To Wai:
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise. 2144-2203 - Gautam Kamath, Vikrant Singhal, Jonathan R. Ullman:
Private Mean Estimation of Heavy-Tailed Distributions. 2204-2235 - Pritish Kamath, Omar Montasser, Nathan Srebro:
Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity. 2236-2262 - Haim Kaplan, Katrina Ligett, Yishay Mansour, Moni Naor, Uri Stemmer:
Privately Learning Thresholds: Closing the Exponential Gap. 2263-2285 - Thomas Kesselheim, Sahil Singla:
Online Learning with Vector Costs and Bandits with Knapsacks. 2286-2305 - Patrick Kidger, Terry J. Lyons:
Universal Approximation with Deep Narrow Networks. 2306-2327 - Johannes Kirschner, Tor Lattimore, Andreas Krause:
Information Directed Sampling for Linear Partial Monitoring. 2328-2369 - Vladimir A. Kobzar, Robert V. Kohn, Zhilei Wang:
New Potential-Based Bounds for Prediction with Expert Advice. 2370-2405 - Gil Kur, Alexander Rakhlin, Adityanand Guntuboyina:
On Suboptimality of Least Squares with Application to Estimation of Convex Bodies. 2406-2424 - Jeongyeol Kwon, Constantine Caramanis:
The EM Algorithm gives Sample-Optimality for Learning Mixtures of Well-Separated Gaussians. 2425-2487 - Tor Lattimore, Csaba Szepesvári:
Exploration by Optimisation in Partial Monitoring. 2488-2515 - Chung-Wei Lee, Haipeng Luo, Mengxiao Zhang:
A Closer Look at Small-loss Bounds for Bandits with Graph Feedback. 2516-2564 - Yin Tat Lee, Ruoqi Shen, Kevin Tian:
Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo. 2565-2597 - Zhixian Lei, Kyle Luh, Prayaag Venkat, Fred Zhang:
A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates. 2598-2612 - Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang:
Learning Over-Parametrized Two-Layer Neural Networks beyond NTK. 2613-2682 - Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai:
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels. 2683-2711 - Yingyu Liang, Hui Yuan:
Learning Entangled Single-Sample Gaussians in the Subset-of-Signals Model. 2712-2737 - Tianyi Lin, Chi Jin
, Michael I. Jordan:
Near-Optimal Algorithms for Minimax Optimization. 2738-2779 - Allen Liu, Ankur Moitra:
Better Algorithms for Estimating Non-Parametric Models in Crowd-Sourcing and Rank Aggregation. 2780-2829 - Nadav Merlis, Shie Mannor:
Tight Lower Bounds for Combinatorial Multi-Armed Bandits. 2830-2857 - Zakaria Mhammedi, Wouter M. Koolen:
Lipschitz and Comparator-Norm Adaptivity in Online Learning. 2858-2887 - Sidhant Misra, Marc Vuffray, Andrey Y. Lokhov:
Information Theoretic Optimal Learning of Gaussian Graphical Models. 2888-2909 - Ankur Moitra, Elchanan Mossel, Colin Sandon:
Parallels Between Phase Transitions and Circuit Complexity? 2910-2946 - Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan:
On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration. 2947-2997 - Mikito Nanashima:
Extending Learnability to Auxiliary-Input Cryptographic Primitives and Meta-PAC Learning. 2998-3029 - Gergely Neu, Nikita Zhivotovskiy:
Fast Rates for Online Prediction with Abstention. 3030-3048 - Gergely Neu, Julia Olkhovskaya:
Efficient and robust algorithms for adversarial linear contextual bandits. 3049-3068 - Yin Tat Lee, Swati Padmanabhan:
An $\widetilde\mathcalO(m/\varepsilon^3.5)$-Cost Algorithm for Semidefinite Programs with Diagonal Constraints. 3069-3119 - Renato Paes Leme, Jon Schneider:
Costly Zero Order Oracles. 3120-3132 - Srinivasan Parthasarathy:
Adaptive Submodular Maximization under Stochastic Item Costs. 3133-3151 - Pierre Perrault, Michal Valko, Vianney Perchet:
Covariance-adapting algorithm for semi-bandits with application to sparse outcomes. 3152-3184 - Guannan Qu, Adam Wierman:
Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning. 3185-3205 - Prasad Raghavendra, Morris Yau:
List Decodable Subspace Recovery. 3206-3226 - Chloé Rouyer, Yevgeny Seldin:
Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits. 3227-3249 - Itay Safran, Ohad Shamir:
How Good is SGD with Random Shuffling? 3250-3284 - Marco Schmalhofer:
A Nearly Optimal Variant of the Perceptron Algorithm for the Uniform Distribution on the Unit Sphere. 3285-3295 - Gil I. Shamir:
Logistic Regression Regret: What's the Catch? 3296-3319 - Max Simchowitz, Karan Singh, Elad Hazan:
Improper Learning for Non-Stochastic Control. 3320-3436 - Thomas Steinke, Lydia Zakynthinou:
Reasoning About Generalization via Conditional Mutual Information. 3437-3452 - Vasilis Syrgkanis, Manolis Zampetakis
:
Estimation and Inference with Trees and Forests in High Dimensions. 3453-3454 - Paxton Turner, Raghu Meka, Philippe Rigollet:
Balancing Gaussian vectors in high dimension. 3455-3486 - Andrew Wagenmaker, Kevin G. Jamieson:
Active Learning for Identification of Linear Dynamical Systems. 3487-3582 - Chen-Yu Wei, Haipeng Luo, Alekh Agarwal:
Taking a hint: How to leverage loss predictors in contextual bandits? 3583-3634 - Blake E. Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro:
Kernel and Rich Regimes in Overparametrized Models. 3635-3673 - Qiaomin Xie, Yudong Chen, Zhaoran Wang, Zhuoran Yang:
Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium. 3674-3682 - Sheng Xu, Zhou Fan, Sahand Negahban:
Tree-projected gradient descent for estimating gradient-sparse parameters on graphs. 3683-3708 - Yun Yang, Zuofeng Shang, Guang Cheng:
Non-asymptotic Analysis for Nonparametric Testing. 3709-3755 - Gilad Yehudai, Ohad Shamir:
Learning a Single Neuron with Gradient Methods. 3756-3786 - Xiao-Tong Yuan, Ping Li:
Nearly Non-Expansive Bounds for Mahalanobis Hard Thresholding. 3787-3813 - Kelvin Shuangjian Zhang, Gabriel Peyré, Jalal Fadili, Marcelo Pereyra:
Wasserstein Control of Mirror Langevin Monte Carlo. 3814-3841 - Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo:
Open Problem: Model Selection for Contextual Bandits. 3842-3846 - Tomer Koren, Shahar Segal:
Open Problem: Tight Convergence of SGD in Constant Dimension. 3847-3851 - Yuetian Luo, Anru R. Zhang:
Open Problem: Average-Case Hardness of Hypergraphic Planted Clique Detection. 3852-3856 - Thomas Steinke, Lydia Zakynthinou:
Open Problem: Information Complexity of VC Learning. 3857-3863 - Tim van Erven, Dirk van der Hoeven, Wojciech Kotlowski, Wouter M. Koolen:
Open Problem: Fast and Optimal Online Portfolio Selection. 3864-3869
![](https://dblp.org/img/cog.dark.24x24.png)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.