Sarath Pattathil
7 papers · 2020–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (3) πΊοΈ Taxonomy Completionist (14)
β
The Questioner
Conferences
AISTATS (2)
COLT (2)
NIPS (2)
ICML (1)
Top co-authors
Keywords
convergence rate
(2)
saddle point
(2)
sample efficiency
(1)
convex optimization
(1)
game theory
(1)
function approximation
(1)
primal-dual optimization
(1)
regret bound
(1)
minimax optimization
(1)
markov decision process
(1)
multi-agent learning
(1)
linear programming
(1)
no-regret learning
(1)
generalization bound
(1)
natural policy gradient
(1)
offline reinforcement learning
(1)
zero-sum game
(1)
repeated auction
(1)
last-iterate convergence
(1)
learning theory
(1)
Papers
Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
COLT 2024
Symmetric (Optimistic) Natural Policy Gradient for Multi-Agent Learning with Parameter Convergence
AISTATS 2023
Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
ICML 2023
What is a Good Metric to Study Generalization of Minimax Learners?
NIPS 2022
Tight last-iterate convergence rates for no-regret learning in multi-player games
NIPS 2020
Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems
COLT 2020
A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
AISTATS 2020