Sarath Pattathil
Sarath Pattathil
Dirección de correo verificada de - Página principal
Citado por
Citado por
A unified analysis of extra-gradient and optimistic gradient methods for saddle point problems: Proximal point approach
A Mokhtari, A Ozdaglar, S Pattathil
International Conference on Artificial Intelligence and Statistics, 1497-1507, 2020
Convergence Rate of for Optimistic Gradient and Extragradient Methods in Smooth Convex-Concave Saddle Point Problems
A Mokhtari, AE Ozdaglar, S Pattathil
SIAM Journal on Optimization 30 (4), 3230-3251, 2020
Last iterate is slower than averaged iterate in smooth convex-concave saddle point problems
N Golowich, S Pattathil, C Daskalakis, A Ozdaglar
Conference on Learning Theory, 1758-1784, 2020
Tight last-iterate convergence rates for no-regret learning in multi-player games
N Golowich, S Pattathil, C Daskalakis
34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
Opportunistic scheduling as restless bandits
VS Borkar, GS Kasbekar, S Pattathil, PY Shetty
IEEE Transactions on Control of Network Systems 5 (4), 1952-1961, 2017
An optimal multistage stochastic gradient method for minimax problems
A Fallah, A Ozdaglar, S Pattathil
2020 59th IEEE Conference on Decision and Control (CDC), 3573-3579, 2020
Concentration bounds for two time scale stochastic approximation
VS Borkar, S Pattathil
2018 56th Annual Allerton Conference on Communication, Control, and …, 2018
A Decentralized Proximal Point-type Method for Non-convex Non-concave Saddle Point Problems
W Liu, A Mokhtari, A Ozdaglar, S Pattathil, Z Shen, N Zheng
34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
Massive machine-type communication (mMTC) access with integrated authentication
NK Pratas, S Pattathil, Č Stefanović, P Popovski
2017 IEEE International Conference on Communications (ICC), 1-6, 2017
Whittle indexability in egalitarian processor sharing systems
VS Borkar, S Pattathil
Annals of Operations Research 317 (2), 417-437, 2022
Revisiting the linear-programming framework for offline rl with general function approximation
AE Ozdaglar, S Pattathil, J Zhang, K Zhang
International Conference on Machine Learning, 26769-26791, 2023
Optimal adaptive testing for epidemic control: combining molecular and serology tests
D Acemoglu, A Fallah, A Giometto, D Huttenlocher, A Ozdaglar, F Parise, ...
Automatica 160, 111391, 2024
Autobidders with budget and roi constraints: Efficiency, regret, and pacing dynamics
B Lucier, S Pattathil, A Slivkins, M Zhang
The Thirty Seventh Annual Conference on Learning Theory, 3642-3643, 2024
Symmetric (optimistic) natural policy gradient for multi-agent learning with parameter convergence
S Pattathil, K Zhang, A Ozdaglar
International Conference on Artificial Intelligence and Statistics, 5641-5685, 2023
What is a good metric to study generalization of minimax learners?
A Ozdaglar, S Pattathil, J Zhang, K Zhang
Advances in Neural Information Processing Systems 35, 38190-38203, 2022
Controlling G-AIMD by index policy
KE Avrachenkov, VS Borkar, S Pattathil
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 120-125, 2017
Learning, diversity and adaptation in changing environments: The role of weak links
D Acemoglu, A Ozdaglar, S Pattathil
National Bureau of Economic Research, 2023
Distributed server allocation for content delivery networks
S Pattathil, VS Borkar, GS Kasbekar
Queueing Models and Service Management 2 (2), 2017
Persistence of the Jordan center in random growing trees
S Pattathil, N Karamchandani, D Shah
2018 IEEE/ACM International Conference on Advances in Social Networks …, 2018
Optimization and Generalization of Minimax Algorithms
S Pattathil
Massachusetts Institute of Technology, 2023
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20