| Spectrally-normalized margin bounds for neural networks PL Bartlett, DJ Foster, MJ Telgarsky Advances in neural information processing systems 30, 2017 | 1661 | 2017 |
| Lower bounds for non-convex stochastic optimization Y Arjevani, Y Carmon, JC Duchi, DJ Foster, N Srebro, B Woodworth Mathematical Programming 199 (1), 165-214, 2023 | 509 | 2023 |
| Orthogonal statistical learning DJ Foster, V Syrgkanis The Annals of Statistics 51 (3), 879-908, 2023 | 366 | 2023 |
| Beyond ucb: Optimal and efficient contextual bandits with regression oracles D Foster, A Rakhlin International conference on machine learning, 3199-3210, 2020 | 302 | 2020 |
| The statistical complexity of interactive decision making DJ Foster, SM Kakade, J Qian, A Rakhlin arXiv preprint arXiv:2112.13487, 2021 | 286 | 2021 |
| Naive exploration is optimal for online lqr M Simchowitz, D Foster International Conference on Machine Learning, 8937-8948, 2020 | 263 | 2020 |
| Independent policy gradient methods for competitive reinforcement learning C Daskalakis, DJ Foster, N Golowich Advances in neural information processing systems 33, 5527-5540, 2020 | 255 | 2020 |
| Practical contextual bandits with regression oracles D Foster, A Agarwal, M Dudík, H Luo, R Schapire International Conference on Machine Learning, 1539-1548, 2018 | 180 | 2018 |
| Adapting to misspecification in contextual bandits DJ Foster, C Gentile, M Mohri, J Zimmert Advances in Neural Information Processing Systems 33, 11478-11489, 2020 | 142 | 2020 |
| Learning in games: Robustness of fast convergence DJ Foster, Z Li, T Lykouris, K Sridharan, E Tardos Advances In Neural Information Processing Systems, 4734-4742, 2016 | 140 | 2016 |
| Instance-dependent complexity of contextual bandits and reinforcement learning: A disagreement-based perspective DJ Foster, A Rakhlin, D Simchi-Levi, Y Xu arXiv preprint arXiv:2010.03104, 2020 | 131 | 2020 |
| Model selection for contextual bandits DJ Foster, A Krishnamurthy, H Luo Advances in Neural Information Processing Systems 32, 2019 | 129 | 2019 |
| Logistic regression: The importance of being improper DJ Foster, S Kale, H Luo, M Mohri, K Sridharan Conference on learning theory, 167-208, 2018 | 121 | 2018 |
| The role of coverage in online reinforcement learning T Xie, DJ Foster, Y Bai, N Jiang, SM Kakade arXiv preprint arXiv:2210.04157, 2022 | 110 | 2022 |
| Learning nonlinear dynamical systems from a single trajectory D Foster, T Sarkar, A Rakhlin Learning for Dynamics and Control, 851-861, 2020 | 107 | 2020 |
| Uniform convergence of gradients for non-convex learning and optimization DJ Foster, A Sekhari, K Sridharan Advances in neural information processing systems 31, 2018 | 103 | 2018 |
| Logarithmic regret for adversarial online control D Foster, M Simchowitz International Conference on Machine Learning, 3211-3221, 2020 | 98 | 2020 |
| Exploratory preference optimization: Harnessing implicit q*-approximation for sample-efficient rlhf T Xie, DJ Foster, A Krishnamurthy, C Rosset, A Awadallah, A Rakhlin arXiv preprint arXiv:2405.21046, 2024 | 94 | 2024 |
| Offline reinforcement learning: Fundamental barriers for value function approximation DJ Foster, A Krishnamurthy, D Simchi-Levi, Y Xu arXiv preprint arXiv:2111.10919, 2021 | 94 | 2021 |
| Parameter-free online learning via model selection DJ Foster, S Kale, M Mohri, K Sridharan Advances in Neural Information Processing Systems 30, 2017 | 86 | 2017 |
Alexander RakhlinProfessor, MITVerified email at mit.edu
