English

A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach

Optimization and Control 2019-09-06 v4 Machine Learning Machine Learning

Abstract

In this paper we consider solving saddle point problems using two variants of Gradient Descent-Ascent algorithms, Extra-gradient (EG) and Optimistic Gradient Descent Ascent (OGDA) methods. We show that both of these algorithms admit a unified analysis as approximations of the classical proximal point method for solving saddle point problems. This viewpoint enables us to develop a new framework for analyzing EG and OGDA for bilinear and strongly convex-strongly concave settings. Moreover, we use the proximal point approximation interpretation to generalize the results for OGDA for a wide range of parameters.

Keywords

Cite

@article{arxiv.1901.08511,
  title  = {A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach},
  author = {Aryan Mokhtari and Asuman Ozdaglar and Sarath Pattathil},
  journal= {arXiv preprint arXiv:1901.08511},
  year   = {2019}
}

Comments

25 pages, 3 figures

R2 v1 2026-06-23T07:21:23.820Z