Saved in:
Bibliographic Details
Main Authors: Kim, Junhyung Lyle, Gidel, Gauthier, Kyrillidis, Anastasios, Pedregosa, Fabian
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2211.04659
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916120041095168
author Kim, Junhyung Lyle
Gidel, Gauthier
Kyrillidis, Anastasios
Pedregosa, Fabian
author_facet Kim, Junhyung Lyle
Gidel, Gauthier
Kyrillidis, Anastasios
Pedregosa, Fabian
contents The extragradient method has gained popularity due to its robust convergence properties for differentiable games. Unlike single-objective optimization, game dynamics involve complex interactions reflected by the eigenvalues of the game vector field's Jacobian scattered across the complex plane. This complexity can cause the simple gradient method to diverge, even for bilinear games, while the extragradient method achieves convergence. Building on the recently proven accelerated convergence of the momentum extragradient method for bilinear games \citep{azizian2020accelerating}, we use a polynomial-based analysis to identify three distinct scenarios where this method exhibits further accelerated convergence. These scenarios encompass situations where the eigenvalues reside on the (positive) real line, lie on the real line alongside complex conjugates, or exist solely as complex conjugates. Furthermore, we derive the hyperparameters for each scenario that achieve the fastest convergence rate.
format Preprint
id arxiv_https___arxiv_org_abs_2211_04659
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle When is Momentum Extragradient Optimal? A Polynomial-Based Analysis
Kim, Junhyung Lyle
Gidel, Gauthier
Kyrillidis, Anastasios
Pedregosa, Fabian
Machine Learning
Optimization and Control
The extragradient method has gained popularity due to its robust convergence properties for differentiable games. Unlike single-objective optimization, game dynamics involve complex interactions reflected by the eigenvalues of the game vector field's Jacobian scattered across the complex plane. This complexity can cause the simple gradient method to diverge, even for bilinear games, while the extragradient method achieves convergence. Building on the recently proven accelerated convergence of the momentum extragradient method for bilinear games \citep{azizian2020accelerating}, we use a polynomial-based analysis to identify three distinct scenarios where this method exhibits further accelerated convergence. These scenarios encompass situations where the eigenvalues reside on the (positive) real line, lie on the real line alongside complex conjugates, or exist solely as complex conjugates. Furthermore, we derive the hyperparameters for each scenario that achieve the fastest convergence rate.
title When is Momentum Extragradient Optimal? A Polynomial-Based Analysis
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2211.04659