Saved in:
Bibliographic Details
Main Authors: Chao, Yutong, Etesami, Jalal
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.11835
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914325014249472
author Chao, Yutong
Etesami, Jalal
author_facet Chao, Yutong
Etesami, Jalal
contents We consider the problem of finding a Nash equilibrium (NE) in a general-sum game, where player $i$'s objective is $f_i(x)=f_i(x_1,...,x_n)$, with $x_j\in\mathbb{R}^{d_j}$ denoting the strategy variables of player $j$. Our focus is on investigating first-order gradient-based algorithms and their variations, such as the block coordinate descent (BCD) algorithm, for tackling this problem. We introduce a set of conditions, called the $n$-sided PL condition, which extends the well-established gradient dominance condition a.k.a Polyak-Łojasiewicz (PL) condition and the concept of multi-convexity. This condition, satisfied by various classes of non-convex functions, allows us to analyze the convergence of various gradient descent (GD) algorithms. Moreover, our study delves into scenarios where the standard gradient descent methods fail to converge to NE. In such cases, we propose adapted variants of GD that converge towards NE and analyze their convergence rates. Finally, we evaluate the performance of the proposed algorithms through several experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11835
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Global Convergence to Nash Equilibrium in Nonconvex General-Sum Games under the $n$-Sided PL Condition
Chao, Yutong
Etesami, Jalal
Computer Science and Game Theory
Multiagent Systems
Numerical Analysis
91A06
G.1.6
We consider the problem of finding a Nash equilibrium (NE) in a general-sum game, where player $i$'s objective is $f_i(x)=f_i(x_1,...,x_n)$, with $x_j\in\mathbb{R}^{d_j}$ denoting the strategy variables of player $j$. Our focus is on investigating first-order gradient-based algorithms and their variations, such as the block coordinate descent (BCD) algorithm, for tackling this problem. We introduce a set of conditions, called the $n$-sided PL condition, which extends the well-established gradient dominance condition a.k.a Polyak-Łojasiewicz (PL) condition and the concept of multi-convexity. This condition, satisfied by various classes of non-convex functions, allows us to analyze the convergence of various gradient descent (GD) algorithms. Moreover, our study delves into scenarios where the standard gradient descent methods fail to converge to NE. In such cases, we propose adapted variants of GD that converge towards NE and analyze their convergence rates. Finally, we evaluate the performance of the proposed algorithms through several experiments.
title Global Convergence to Nash Equilibrium in Nonconvex General-Sum Games under the $n$-Sided PL Condition
topic Computer Science and Game Theory
Multiagent Systems
Numerical Analysis
91A06
G.1.6
url https://arxiv.org/abs/2602.11835