Saved in:
Bibliographic Details
Main Authors: Abe, Kenshi, Sakamoto, Mitsuki, Ariu, Kaito, Iwasaki, Atsushi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.05747
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917549805928448
author Abe, Kenshi
Sakamoto, Mitsuki
Ariu, Kaito
Iwasaki, Atsushi
author_facet Abe, Kenshi
Sakamoto, Mitsuki
Ariu, Kaito
Iwasaki, Atsushi
contents This paper proposes asymmetric perturbation, where only one player's payoff function is perturbed, for solving bilinear saddle-point optimization problems, commonly arising in minimax problems, game theory, and constrained optimization. Symmetric perturbation is known to require decreasing its strength to ensure convergence to a solution, i.e., an equilibrium in the original game, resulting in a slower rate. First, with asymmetric perturbation, we show that, for a sufficiently small perturbation strength, the equilibrium strategy of the asymmetrically perturbed game coincides with an equilibrium strategy of the original unperturbed game. Second, building on this coincidence, we construct a learning algorithm with a linear last-iterate convergence rate. Third, motivated by the fact that the coincidence relies on the perturbation strength being sufficiently small, we also provide a parameter-free variant, retaining the linear rate. Finally, we empirically demonstrate fast convergence toward equilibria in both normal-form and extensive-form games.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
Abe, Kenshi
Sakamoto, Mitsuki
Ariu, Kaito
Iwasaki, Atsushi
Optimization and Control
This paper proposes asymmetric perturbation, where only one player's payoff function is perturbed, for solving bilinear saddle-point optimization problems, commonly arising in minimax problems, game theory, and constrained optimization. Symmetric perturbation is known to require decreasing its strength to ensure convergence to a solution, i.e., an equilibrium in the original game, resulting in a slower rate. First, with asymmetric perturbation, we show that, for a sufficiently small perturbation strength, the equilibrium strategy of the asymmetrically perturbed game coincides with an equilibrium strategy of the original unperturbed game. Second, building on this coincidence, we construct a learning algorithm with a linear last-iterate convergence rate. Third, motivated by the fact that the coincidence relies on the perturbation strength being sufficiently small, we also provide a parameter-free variant, retaining the linear rate. Finally, we empirically demonstrate fast convergence toward equilibria in both normal-form and extensive-form games.
title Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
topic Optimization and Control
url https://arxiv.org/abs/2506.05747