Search Results for author:
Found 7 papers, 1 papers with code
Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence
This paper revisits the convergence of Stochastic Mirror Descent (SMD) in the contemporary nonconvex optimization setting.
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence
Our main results are two-fold: (i) in the deterministic setting, we establish the first global last-iterate linear convergence result for the nested algorithm that seeks NE of zero-sum LQ games; (ii) in the model-free setting, we establish a~$\widetilde{\mathcal{O}}(\epsilon^{-2})$ sample complexity using a single-point ZO estimator.
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
We consider the reinforcement learning (RL) problem with general utilities which consists in maximizing a function of the state-action occupancy measure.
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
Recently, the impressive empirical success of policy gradient (PG) methods has catalyzed the development of their theoretical foundations.
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 for communication-efficient training -- three point compressors (3PC) -- as well as efficient distributed nonconvex optimization algorithms that can take advantage of them.
EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback
First proposed by Seide (2014) as a heuristic, error feedback (EF) is a very popular mechanism for enforcing convergence of distributed gradient-based optimization methods enhanced with communication compression strategies based on the application of contractive compression operators.
EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback
However, all existing analyses either i) apply to the single node setting only, ii) rely on very strong and often unreasonable assumptions, such global boundedness of the gradients, or iterate-dependent assumptions that cannot be checked a-priori and may not hold in practice, or iii) circumvent these issues via the introduction of additional unbiased compressors, which increase the communication cost.
