| On the theory of policy gradient methods: Optimality, approximation, and distribution shift A Agarwal, SM Kakade, JD Lee, G Mahajan Journal of Machine Learning Research 22 (98), 1-76, 2021 | 679 | 2021 |
| Optimality and approximation with policy gradient methods in markov decision processes A Agarwal, SM Kakade, JD Lee, G Mahajan Conference on learning theory, 64-66, 2020 | 451 | 2020 |
| Bilinear classes: A structural framework for provable generalization in rl S Du, S Kakade, J Lee, S Lovett, G Mahajan, W Sun, R Wang International Conference on Machine Learning, 2826-2836, 2021 | 286 | 2021 |
| Agnostic -learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity SS Du, JD Lee, G Mahajan, R Wang Advances in Neural Information Processing Systems 33, 22327-22337, 2020 | 68* | 2020 |
| Realizable learning is all you need M Hopkins, DM Kane, S Lovett, G Mahajan Conference on Learning Theory, 3015-3069, 2022 | 39 | 2022 |
| Computational-statistical gap in reinforcement learning D Kane, S Liu, S Lovett, G Mahajan Conference on Learning Theory, 1282-1302, 2022 | 34 | 2022 |
| Noise-tolerant, reliable active classification with comparison queries M Hopkins, D Kane, S Lovett, G Mahajan Conference on Learning Theory, 1957-2006, 2020 | 33 | 2020 |
| Point location and active learning: Learning halfspaces almost optimally M Hopkins, D Kane, S Lovett, G Mahajan 2020 IEEE 61st Annual Symposium on Foundations of Computer Science (FOCS …, 2020 | 24 | 2020 |
| Learning hidden markov models using conditional samples SM Kakade, A Krishnamurthy, G Mahajan, C Zhang arXiv preprint arXiv:2302.14753, 2023 | 12* | 2023 |
| Exponential hardness of reinforcement learning with linear function approximation S Liu, G Mahajan, D Kane, S Lovett, G Weisz, C Szepesvári The Thirty Sixth Annual Conference on Learning Theory, 1588-1617, 2023 | 11* | 2023 |
| Convergence of online k-means G So, G Mahajan, S Dasgupta International Conference on Artificial Intelligence and Statistics, 8534-8569, 2022 | 8 | 2022 |
| Do PAC-Learners Learn the Marginal Distribution? M Hopkins, DM Kane, S Lovett, G Mahajan arXiv preprint arXiv:2302.06285, 2023 | 6 | 2023 |
| Improved classical shadows from local symmetries in the Schur basis D Grier, S Liu, G Mahajan arXiv preprint arXiv:2405.09525, 2024 | 3 | 2024 |
| Learning what to remember R Bhattacharjee, G Mahajan International Conference on Algorithmic Learning Theory, 70-89, 2022 | 2 | 2022 |
| Short course on RL theory G Mahajan | | 2025 |
| Computational and Statistical Complexity of Learning in Sequential Models G Mahajan University of California, San Diego, 2023 | | 2023 |
| Convergence of online -means S Dasgupta, G Mahajan, G So arXiv preprint arXiv:2202.10640, 2022 | | 2022 |
Jason D. LeeAssociate Professor of EECS & Statistics at UC BerkeleyVerified email at princeton.edu
