Enregistré dans:
Détails bibliographiques
Auteurs principaux: Compagnoni, Enea Monzio, Orvieto, Antonio, Kersting, Hans, Proske, Frank Norbert, Lucchi, Aurelien
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.12508
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910336453443584
author Compagnoni, Enea Monzio
Orvieto, Antonio
Kersting, Hans
Proske, Frank Norbert
Lucchi, Aurelien
author_facet Compagnoni, Enea Monzio
Orvieto, Antonio
Kersting, Hans
Proske, Frank Norbert
Lucchi, Aurelien
contents Minimax optimization problems have attracted a lot of attention over the past few years, with applications ranging from economics to machine learning. While advanced optimization methods exist for such problems, characterizing their dynamics in stochastic scenarios remains notably challenging. In this paper, we pioneer the use of stochastic differential equations (SDEs) to analyze and compare Minimax optimizers. Our SDE models for Stochastic Gradient Descent-Ascent, Stochastic Extragradient, and Stochastic Hamiltonian Gradient Descent are provable approximations of their algorithmic counterparts, clearly showcasing the interplay between hyperparameters, implicit regularization, and implicit curvature-induced noise. This perspective also allows for a unified and simplified analysis strategy based on the principles of Itô calculus. Finally, our approach facilitates the derivation of convergence conditions and closed-form solutions for the dynamics in simplified settings, unveiling further insights into the behavior of different optimizers.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12508
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SDEs for Minimax Optimization
Compagnoni, Enea Monzio
Orvieto, Antonio
Kersting, Hans
Proske, Frank Norbert
Lucchi, Aurelien
Machine Learning
Optimization and Control
Minimax optimization problems have attracted a lot of attention over the past few years, with applications ranging from economics to machine learning. While advanced optimization methods exist for such problems, characterizing their dynamics in stochastic scenarios remains notably challenging. In this paper, we pioneer the use of stochastic differential equations (SDEs) to analyze and compare Minimax optimizers. Our SDE models for Stochastic Gradient Descent-Ascent, Stochastic Extragradient, and Stochastic Hamiltonian Gradient Descent are provable approximations of their algorithmic counterparts, clearly showcasing the interplay between hyperparameters, implicit regularization, and implicit curvature-induced noise. This perspective also allows for a unified and simplified analysis strategy based on the principles of Itô calculus. Finally, our approach facilitates the derivation of convergence conditions and closed-form solutions for the dynamics in simplified settings, unveiling further insights into the behavior of different optimizers.
title SDEs for Minimax Optimization
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2402.12508