Follow
Eric Mazumdar
Eric Mazumdar
Verified email at caltech.edu - Homepage
Title
Cited by
Cited by
Year
On gradient-based learning in continuous games
E Mazumdar, LJ Ratliff, SS Sastry
SIAM Journal on Mathematics of Data Science 2 (1), 103-131, 2020
176*2020
On finding local nash equilibria (and only local nash equilibria) in zero-sum games
EV Mazumdar, MI Jordan, SS Sastry
arXiv preprint arXiv:1901.00838, 2019
1442019
Feedback linearization for uncertain systems via reinforcement learning
T Westenbroek, D Fridovich-Keil, E Mazumdar, S Arora, V Prabhu, ...
2020 IEEE International Conference on Robotics and Automation (ICRA), 1364-1371, 2020
59*2020
Mathematical framework for activity-based cancer biomarkers
GA Kwong, JS Dudani, E Carrodeguas, EV Mazumdar, SM Zekavat, ...
Proceedings of the National Academy of Sciences 112 (41), 12627-12632, 2015
522015
Gradient-based inverse risk-sensitive reinforcement learning
E Mazumdar, LJ Ratliff, T Fiez, SS Sastry
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 5796-5801, 2017
46*2017
Who Leads and Who Follows in Strategic Classification?
T Zrnic, E Mazumdar, S Sastry, M Jordan
Advances in Neural Information Processing Systems 34, 15257-15269, 2021
432021
Convergence Guarantees for Gradient-Based Learning in Continuous Games.
B Chasnov, LJ Ratliff, E Mazumdar, S Burden
Uncertainty in artificial intelligence, 2019
42*2019
On approximate Thompson sampling with Langevin algorithms
E Mazumdar, A Pacchiano, Y Ma, M Jordan, P Bartlett
International Conference on Machine Learning, 6797-6807, 2020
40*2020
Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games
E Mazumdar, LJ Ratliff, MI Jordan, SS Sastry
arXiv preprint arXiv:1907.03712, 2019
40*2019
Fast distributionally robust learning with variance-reduced min-max optimization
Y Yu, T Lin, EV Mazumdar, M Jordan
International Conference on Artificial Intelligence and Statistics, 1219-1250, 2022
252022
Global convergence to local minmax equilibrium in classes of nonconvex zero-sum games
T Fiez, L Ratliff, E Mazumdar, E Faulkner, A Narang
Advances in Neural Information Processing Systems 34, 29049-29063, 2021
212021
Langevin monte carlo for contextual bandits
P Xu, H Zheng, EV Mazumdar, K Azizzadenesheli, A Anandkumar
International Conference on Machine Learning, 24830-24850, 2022
192022
Zeroth-order methods for convex-concave min-max problems: Applications to decision-dependent risk minimization
C Maheshwari, CY Chiu, E Mazumdar, S Sastry, L Ratliff
International Conference on Artificial Intelligence and Statistics, 6702-6734, 2022
172022
To observe or not to observe: Queuing game framework for urban parking
LJ Ratliff, C Dowling, E Mazumdar, B Zhang
2016 IEEE 55th Conference on Decision and Control (CDC), 5286-5291, 2016
172016
Local Nash Equilibria are Isolated, Strict Local Nash Equilibria in 'Almost All' Zero-Sum Continuous Games
E Mazumdar, L Ratliff
arXiv preprint arXiv:2002.01007, 2020
132020
Understanding the impact of parking on urban mobility via routing games on queue-flow networks
D Calderone, E Mazumdar, LJ Ratliff, SS Sastry
2016 IEEE 55th Conference on Decision and Control (CDC), 7605-7610, 2016
132016
On the analysis of cyclic drug schedules for cancer treatment using switched dynamical systems
MP Chapman, EV Mazumdar, E Langer, R Sears, CJ Tomlin
2018 IEEE Conference on Decision and Control (CDC), 3503-3509, 2018
102018
A multi-armed bandit approach for online expert selection in markov decision processes
E Mazumdar, R Dong, VR Royo, C Tomlin, SS Sastry
arXiv preprint arXiv:1707.05714, 2017
102017
Adaptive control for linearizable systems using on-policy reinforcement learning
T Westenbroek, E Mazumdar, D Fridovich-Keil, V Prabhu, CJ Tomlin, ...
2020 59th IEEE Conference on Decision and Control (CDC), 118-125, 2020
92020
A finite-sample analysis of payoff-based independent learning in zero-sum stochastic games
Z Chen, K Zhang, E Mazumdar, A Ozdaglar, A Wierman
Advances in Neural Information Processing Systems 36, 2024
82024
The system can't perform the operation now. Try again later.
Articles 1–20