The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Daskalakis, Constantinos, Panageas, Ioannis
Formato: Preprint
Publicado: 2018
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916970483417088
author Daskalakis, Constantinos
Panageas, Ioannis
author_facet Daskalakis, Constantinos
Panageas, Ioannis
contents Motivated by applications in Optimization, Game Theory, and the training of Generative Adversarial Networks, the convergence properties of first order methods in min-max problems have received extensive study. It has been recognized that they may cycle, and there is no good understanding of their limit points when they do not. When they converge, do they converge to local min-max solutions? We characterize the limit points of two basic first order methods, namely Gradient Descent/Ascent (GDA) and Optimistic Gradient Descent Ascent (OGDA). We show that both dynamics avoid unstable critical points for almost all initializations. Moreover, for small step sizes and under mild assumptions, the set of \{OGDA\}-stable critical points is a superset of \{GDA\}-stable critical points, which is a superset of local min-max solutions (strict in some cases). The connecting thread is that the behavior of these dynamics can be studied from a dynamical systems perspective.
format Preprint
id arxiv_https___arxiv_org_abs_1807_03907
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
Daskalakis, Constantinos
Panageas, Ioannis
Optimization and Control
Machine Learning
Motivated by applications in Optimization, Game Theory, and the training of Generative Adversarial Networks, the convergence properties of first order methods in min-max problems have received extensive study. It has been recognized that they may cycle, and there is no good understanding of their limit points when they do not. When they converge, do they converge to local min-max solutions? We characterize the limit points of two basic first order methods, namely Gradient Descent/Ascent (GDA) and Optimistic Gradient Descent Ascent (OGDA). We show that both dynamics avoid unstable critical points for almost all initializations. Moreover, for small step sizes and under mild assumptions, the set of \{OGDA\}-stable critical points is a superset of \{GDA\}-stable critical points, which is a superset of local min-max solutions (strict in some cases). The connecting thread is that the behavior of these dynamics can be studied from a dynamical systems perspective.
title The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/1807.03907