Seuraa
Amrit Singh Bedi
Amrit Singh Bedi
Muut nimetAmrit S. Bedi
Research Scientist at University of Maryland, College Park, MD, USA.
Vahvistettu sähköpostiosoite verkkotunnuksessa umd.edu - Kotisivu
Nimike
Viittaukset
Viittaukset
Vuosi
Variational policy gradient method for reinforcement learning with general utilities
J Zhang, A Koppel, AS Bedi, C Szepesvari, M Wang
Advances in Neural Information Processing Systems 33, 2020
722020
Online Learning With Inexact Proximal Online Gradient Descent Algorithms
R Dixit, AS Bedi, R Tripathi, K Rajawat
IEEE Transactions on Signal Processing 67 (5), 1338 - 1352, 2019
682019
GADMM: Fast and communication efficient framework for distributed machine learning
A Elgabli, J Park, AS Bedi, M Bennis, V Aggarwal
Journal of Machine Learning Research 21 (76), 1-39, 2020
622020
Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
A Elgabli, J Park, AS Bedi, M Bennis, V Aggarwal
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
372020
Asynchronous Incremental Stochastic Dual Descent Algorithm for Network Resource Allocation
AS Bedi, K Rajawat
IEEE Transactions on Signal Processing, 2018
322018
Tracking Moving Agents via Inexact Online Gradient Descent Algorithm
AS Bedi, P Sarma, K Rajawat
IEEE Journal of Selected Topics in Signal Processing 12 (1), 202-217, 2018
292018
Cautious reinforcement learning via distributional risk in the dual domain
J Zhang, AS Bedi, M Wang, A Koppel
arXiv preprint arXiv:2002.12475, 2020
202020
Achieving zero constraint violation for constrained reinforcement learning via primal-dual approach
Q Bai, AS Bedi, M Agarwal, A Koppel, V Aggarwal
Proceedings of the AAAI Conference on Artificial Intelligence 36 (4), 3682-3689, 2022
182022
Asynchronous and parallel distributed pose graph optimization
Y Tian, A Koppel, AS Bedi, JP How
IEEE Robotics and Automation Letters 5 (4), 5819-5826, 2020
182020
Asynchronous online learning in multi-agent systems with proximity constraints
AS Bedi, A Koppel, K Rajawat
IEEE Transactions on Signal and Information Processing over Networks 5 (3 …, 2019
172019
Asynchronous Saddle Point Algorithm for Stochastic Optimization in Heterogeneous Networks
AS Bedi, A Koppel, K Rajawat
IEEE Transactions on Signal Processing 67 (7), 1742 - 1757, 2019
172019
BER-optimized precoders for OFDM systems with insufficient cyclic prefix
AS Bedi, J Akhtar, K Rajawat, AK Jagannatham
IEEE Communications Letters 20 (2), 280-283, 2015
132015
Online learning over dynamic graphs via distributed proximal gradient algorithm
R Dixit, AS Bedi, K Rajawat
IEEE Transactions on Automatic Control, 2020
122020
Conservative stochastic optimization with expectation constraints
Z Akhtar, AS Bedi, K Rajawat
IEEE Transactions on Signal Processing 69, 3190-3205, 2021
112021
Controlling the Bias-Variance Tradeoff via Coherent Risk for Robust Learning with Kernels
A Koppel, AS Bedi, K Rajawat
American Control Conference (ACC), Philadelphia, PA, USA, July 10-12, 2019., 0
11*
Online algorithms for storage utilization under real-time pricing in smart grid
SA Amrit S. Bedi, , P.V. Aditya P., , Md. Waseem Ahmad, , S. Swapnil ...
International Journal of Electrical Power & Energy Systems 101, 50-59, 2018
102018
Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning
AS Bedi, A Koppel, K Rajawat
IEEE Transactions on Signal Processing (Submitted), 0
10*
Dynamic Online Learning via Frank-Wolfe Algorithm
DS Kalhan, AS Bedi, A Koppel, K Rajawat, H Hassani, AK Gupta, ...
IEEE Transactions on Signal Processing 69, 932-947, 2021
92021
Beyond consensus and synchrony in decentralized online optimization using saddle point method
AS Bedi, A Koppel, K Rajawat
51st Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA., 2017
92017
MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
J Zhang, AS Bedi, M Wang, A Koppel
arXiv preprint arXiv:2106.00543, 2021
82021
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–20