Follow
Gaurav Mahajan
Title
Cited by
Cited by
Year
Optimality and approximation with policy gradient methods in markov decision processes
A Agarwal, SM Kakade, JD Lee, G Mahajan
Conference on Learning Theory (COLT 2020), 2020
2562020
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 (JMLR 2021), 2021
1462021
Bilinear classes: A structural framework for provable generalization in rl
SS Du, SM Kakade, JD Lee, S Lovett, G Mahajan, W Sun, R Wang
International Conference on Machine Learning (ICML 2021) 139, 2021
862021
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 (NeurIPS 2020), 2020
48*2020
Noise-tolerant, reliable active classification with comparison queries
M Hopkins, D Kane, S Lovett, G Mahajan
Conference on Learning Theory (COLT 2020), 1957-2006, 2020
142020
Point location and active learning: Learning halfspaces almost optimally
M Hopkins, DM Kane, S Lovett, G Mahajan
61st Annual Symposium on Foundations of Computer Science (FOCS 2020), 1034-1044, 2020
92020
Computational-statistical gaps in reinforcement learning
D Kane, S Liu, S Lovett, G Mahajan
Conference on Learning Theory (COLT 2022), 2022
42022
Realizable learning is all you need
M Hopkins, DM Kane, S Lovett, G Mahajan
Conference on Learning Theory (COLT 2022), 3015-3069, 2022
32022
Convergence of online k-means
G So, G Mahajan, S Dasgupta
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2022
12022
Learning what to remember
R Bhattacharjee, G Mahajan
International Conference on Algorithmic Learning Theory (ALT 2022) 167, 70-89, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–10