Solving Matrix Games with Near-Optimal Matvec Complexity

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Karmarkar, Ishani, O'Carroll, Liam, Sidford, Aaron
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912807610482688
author Karmarkar, Ishani
O'Carroll, Liam
Sidford, Aaron
author_facet Karmarkar, Ishani
O'Carroll, Liam
Sidford, Aaron
contents We study the problem of computing an $ε$-approximate Nash equilibrium of a two-player, bilinear game with a bounded payoff matrix $A \in \mathbb{R}^{m \times n}$, when the players' strategies are constrained to lie in simple sets. We provide algorithms which solve this problem in $\tilde{O}(ε^{-2/3})$ matrix-vector multiplies (matvecs) in two well-studied cases: $\ell_1$-$\ell_1$ (or zero-sum) games, where the players' strategies are both in the probability simplex, and $\ell_2$-$\ell_1$ games (encompassing hard-margin SVMs), where the players' strategies are in the unit Euclidean ball and probability simplex respectively. These results improve upon the previous state-of-the-art complexities of $\tilde{O}(ε^{-8/9})$ for $\ell_1$-$\ell_1$ and $\tilde{O}(ε^{-7/9})$ for $\ell_2$-$\ell_1$ due to [KOS '25]. In both settings our results are nearly-optimal as they match lower bounds of [KS '25] up to polylogarithmic factors.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02347
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Solving Matrix Games with Near-Optimal Matvec Complexity
Karmarkar, Ishani
O'Carroll, Liam
Sidford, Aaron
Optimization and Control
Data Structures and Algorithms
Computer Science and Game Theory
We study the problem of computing an $ε$-approximate Nash equilibrium of a two-player, bilinear game with a bounded payoff matrix $A \in \mathbb{R}^{m \times n}$, when the players' strategies are constrained to lie in simple sets. We provide algorithms which solve this problem in $\tilde{O}(ε^{-2/3})$ matrix-vector multiplies (matvecs) in two well-studied cases: $\ell_1$-$\ell_1$ (or zero-sum) games, where the players' strategies are both in the probability simplex, and $\ell_2$-$\ell_1$ games (encompassing hard-margin SVMs), where the players' strategies are in the unit Euclidean ball and probability simplex respectively. These results improve upon the previous state-of-the-art complexities of $\tilde{O}(ε^{-8/9})$ for $\ell_1$-$\ell_1$ and $\tilde{O}(ε^{-7/9})$ for $\ell_2$-$\ell_1$ due to [KOS '25]. In both settings our results are nearly-optimal as they match lower bounds of [KS '25] up to polylogarithmic factors.
title Solving Matrix Games with Near-Optimal Matvec Complexity
topic Optimization and Control
Data Structures and Algorithms
Computer Science and Game Theory
url https://arxiv.org/abs/2601.02347