research
∙
09/08/2023
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity
Zero-sum Linear Quadratic (LQ) games are fundamental in optimal control ...
share
research
∙
06/02/2023
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
We consider the reinforcement learning (RL) problem with general utiliti...
research
∙
05/24/2023
Momentum Provably Improves Error Feedback!
Due to the high communication overhead when training machine learning mo...
research
∙
02/03/2023
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
Recently, the impressive empirical success of policy gradient (PG) metho...
research
∙
02/02/2022
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation
We propose and study a new class of gradient communication mechanisms fo...
research
∙
10/07/2021
EF21 with Bells Whistles: Practical Algorithmic Extensions of Modern Error Feedback
First proposed by Seide (2014) as a heuristic, error feedback (EF) is a ...
research
∙
06/09/2021