关注
Mukul Gagrani
Mukul Gagrani
Qualcomm AI Research
在 usc.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Learning unknown markov decision processes: A thompson sampling approach
Y Ouyang, M Gagrani, A Nayyar, R Jain
Advances in neural information processing systems 30, 2017
1482017
Learning-based control of unknown linear systems with thompson sampling
Y Ouyang, M Gagrani, R Jain
arXiv preprint arXiv:1709.04047, 2017
582017
Control of unknown linear systems with thompson sampling
Y Ouyang, M Gagrani, R Jain
2017 55th Annual Allerton Conference on Communication, Control, and …, 2017
552017
Posterior sampling-based reinforcement learning for control of unknown linear systems
Y Ouyang, M Gagrani, R Jain
IEEE Transactions on Automatic Control 65 (8), 3600-3607, 2019
242019
On noise-enhanced distributed inference in the presence of Byzantines
M Gagrani, P Sharma, S Iyengar, VSS Nadendla, A Vempaty, H Chen, ...
2011 49th Annual Allerton Conference on Communication, Control, and …, 2011
212011
Decentralized minimax control problems with partial history sharing
M Gagrani, A Nayyar
2017 American Control Conference (ACC), 3373-3379, 2017
122017
Optimal scheduling strategy for networked estimation with energy harvesting
MM Vasconcelos, M Gagrani, A Nayyar, U Mitra
IEEE Transactions on Control of Network Systems 7 (4), 1723-1735, 2020
112020
Thompson sampling for some decentralized control problems
M Gagrani, A Nayyar
2018 IEEE Conference on Decision and Control (CDC), 1053-1058, 2018
102018
Neural topological ordering for computation graphs
M Gagrani, C Rainone, Y Yang, H Teague, W Jeon, H Van Hoof
arXiv preprint arXiv:2207.05899, 2022
92022
Worst-case guarantees for remote estimation of an uncertain source
M Gagrani, Y Ouyang, M Rasouli, A Nayyar
IEEE Transactions on Automatic Control 66 (4), 1794-1801, 2020
72020
Thompson sampling for linear quadratic mean-field teams
M Gagrani, S Sudhakara, A Mahajan, A Nayyar, Y Ouyang
2021 60th IEEE Conference on Decision and Control (CDC), 720-727, 2021
62021
Scheduling and estimation strategies in a sequential networked estimation problem
M Gagrani, MM Vasconcelos, A Nayyar
2018 56th Annual Allerton Conference on Communication, Control, and …, 2018
52018
Recursive speculative decoding: Accelerating llm inference via sampling without replacement
W Jeon, M Gagrani, R Goel, J Park, M Lee, C Lott
arXiv preprint arXiv:2402.14160, 2024
32024
A modified Thompson sampling-based learning algorithm for unknown linear systems
M Gagrani, S Sudhakara, A Mahajan, A Nayyar, Y Ouyang
2022 IEEE 61st Conference on Decision and Control (CDC), 6658-6665, 2022
32022
Transmit and receive antenna pairing in MIMO relay networks
M Gagrani, AK Chaturvedi
IEEE Communications Letters 18 (11), 2043-2046, 2014
32014
Neural DAG scheduling via one-shot priority sampling
W Jeon, M Gagrani, B Bartan, WW Zeng, H Teague, P Zappi, C Lott
The Eleventh International Conference on Learning Representations, 2022
22022
A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
M Gagrani, S Sudhakara, A Mahajan, A Nayyar, Y Ouyang
arXiv preprint arXiv:2108.08502, 2021
22021
Weakly coupled constrained Markov decision processes in Borel spaces
M Gagrani, A Nayyar
2020 American Control Conference (ACC), 2790-2795, 2020
22020
On Speculative Decoding for Multimodal Large Language Models
M Gagrani, R Goel, W Jeon, J Park, M Lee, C Lott
arXiv preprint arXiv:2404.08856, 2024
12024
Neural directed acyclic graph (dag) scheduling via one-shot priority sampling
W Jeon, M Gagrani, W Zeng, E Teague, B Bartan, P Zappi, C Lott
US Patent App. 18/464,996, 2024
12024
系统目前无法执行此操作,请稍后再试。
文章 1–20