Goto

Collaborating Authors

 eg method

Main

Main

Neural Information Processing Systems

We also conduct experiments supporting our theoretical results.

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

arXiv.org Machine Learning

We consider solving convex-concave saddle point problems. We focus on two variants of gradient decent-ascent algorithms, Extra-gradient (EG) and Optimistic Gradient (OGDA) methods, and show that they admit a unified analysis as approximations of the classical proximal point method for solving saddle-point problems. This viewpoint enables us to generalize EG (in terms of extrapolation steps) and OGDA (in terms of parameters) and obtain new convergence rate results for these algorithms for the bilinear case as well as the strongly convex-concave case.