Two-timescale Extragradient for Finding Local Minimax Points

05/25/2023
by   Jiseok Chae, et al.
0

Minimax problems are notoriously challenging to optimize. However, we demonstrate that the two-timescale extragradient can be a viable solution. By utilizing dynamical systems theory, we show that it converges to points that satisfy the second-order necessary condition of local minimax points, under a mild condition. This work surpasses all previous results as we eliminate a crucial assumption that the Hessian, with respect to the maximization variable, is nondegenerate.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2022

Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems

In this paper, we consider a class of nonconvex-nonconcave minimax probl...
research
10/10/2021

Finding Second-Order Stationary Point for Nonconvex-Strongly-Concave Minimax Problem

We study the smooth minimax optimization problem of the form min_ xmax_ ...
research
10/16/2019

On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach

Many tasks in modern machine learning can be formulated as finding equil...
research
02/04/2022

A J-Symmetric Quasi-Newton Method for Minimax Problems

Minimax problems have gained tremendous attentions across the optimizati...
research
10/20/2017

First-order Methods Almost Always Avoid Saddle Points

We establish that first-order methods avoid saddle points for almost all...
research
07/13/2020

Relaxing the I.I.D. Assumption: Adaptive Minimax Optimal Sequential Prediction with Expert Advice

We consider sequential prediction with expert advice when the data are g...
research
01/03/2020

Tuning Multigrid Methods with Robust Optimization

Local Fourier analysis is a useful tool for predicting and analyzing the...

Please sign up or login with your details

Forgot password? Click here to reset