| The statistical complexity of interactive decision making DJ Foster, SM Kakade, J Qian, A Rakhlin arXiv preprint arXiv:2112.13487, 2021 | 286 | 2021 |
| Convex and non-convex optimization under generalized smoothness H Li, J Qian, Y Tian, A Rakhlin, A Jadbabaie Advances in Neural Information Processing Systems 36, 40238-40271, 2023 | 103 | 2023 |
| Importance resampling for off-policy prediction M Schlegel, W Chung, D Graves, J Qian, M White Advances in Neural Information Processing Systems 32, 2019 | 52 | 2019 |
| Exploration bonus for regret minimization in discrete and continuous average reward mdps J Qian, R Fruit, M Pirotta, A Lazaric Advances in Neural Information Processing Systems 32, 2019 | 50* | 2019 |
| Model-free reinforcement learning with the decision-estimation coefficient DJ Foster, N Golowich, J Qian, A Rakhlin, A Sekhari Thirty-seventh Conference on Neural Information Processing Systems, 2023 | 36* | 2023 |
| Towards minimax optimal reinforcement learning in factored markov decision processes Y Tian, J Qian, S Sra Advances in Neural Information Processing Systems 33, 19896-19907, 2020 | 35 | 2020 |
| Concentration inequalities for multinoulli random variables J Qian, R Fruit, M Pirotta, A Lazaric arXiv preprint arXiv:2001.11595, 2020 | 24 | 2020 |
| Robust learning under clean-label attack A Blum, S Hanneke, J Qian, H Shao Conference on Learning Theory, 591-634, 2021 | 15 | 2021 |
| Byzantine-robust federated linear bandits A Jadbabaie, H Li, J Qian, Y Tian 2022 IEEE 61st Conference on Decision and Control (CDC), 5206-5213, 2022 | 14 | 2022 |
| Online estimation via offline estimation: An information-theoretic framework DJ Foster, Y Han, J Qian, A Rakhlin Advances in Neural Information Processing Systems 37, 42840-42898, 2024 | 13 | 2024 |
| How Does Variance Shape the Regret in Contextual Bandits? Z Jia, J Qian, A Rakhlin, CY Wei Advances in Neural Information Processing Systems 37, 83730-83785, 2024 | 10 | 2024 |
| Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability F Chen, DJ Foster, Y Han, J Qian, A Rakhlin, Y Xu Advances in Neural Information Processing Systems 37, 75585-75641, 2024 | 10 | 2024 |
| Offline oracle-efficient learning for contextual mdps via layerwise exploration-exploitation tradeoff J Qian, H Hu, D Simchi-Levi Advances in Neural Information Processing Systems 37, 133743-133775, 2024 | 7 | 2024 |
| Refined Risk Bounds for Unbounded Losses via Transductive Priors J Qian, A Rakhlin, N Zhivotovskiy arXiv preprint arXiv:2410.21621, 2024 | 7 | 2024 |
| Bridging multiple worlds: multi-marginal optimal transport for causal partial-identification problem Z Gao, S Ge, J Qian arXiv preprint arXiv:2406.07868, 2024 | 5 | 2024 |
| Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits Y Gu, Y Han, J Qian arXiv preprint arXiv:2503.00273, 2025 | 2 | 2025 |
| The Non-linear -Design and Applications to Interactive Learning A Agarwal, J Qian, A Rakhlin, T Zhang Forty-first International Conference on Machine Learning, 2024 | 1 | 2024 |
| Sigmoid-FTRL: Design-Based Adaptive Neyman Allocation for AIPW Estimators F Chen, S Ge, J Qian, C Harshaw arXiv preprint arXiv:2511.19905, 2025 | | 2025 |
| MUSE: Multi-Treatment Experiment Design for Winner Selection and Effect Estimation J Xu, J Qian, Z Gao arXiv preprint arXiv:2510.04489, 2025 | | 2025 |
| To bootstrap or to rollout? An optimal and adaptive interpolation W Mou, J Qian arXiv preprint arXiv:2411.09731, 2024 | | 2024 |
Alexander RakhlinProfessor, MITVerified email at mit.edu
