Saved in:
Bibliographic Details
Main Authors: Jiang, Jiashuo, Zhang, Mengxiao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.12513
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918335544819712
author Jiang, Jiashuo
Zhang, Mengxiao
author_facet Jiang, Jiashuo
Zhang, Mengxiao
contents In this work, we study the sample complexity of obtaining a Nash equilibrium (NE) estimate in two-player zero-sum matrix games with noisy feedback. Specifically, we propose a novel algorithm that repeatedly solves linear programs (LPs) to obtain an NE estimate with bias at most $\varepsilon$ with a sample complexity of $O\left(\frac{m_1 m_2}{\varepsilon\min\{δ^2,σ_0^2,σ^3\}} \log\frac{m_1 m_2}{\varepsilon}\right)$ for general $m_1 \times m_2$ game matrices, where $σ$, $σ_0$, $δ$ are some problem-dependent constants. To our knowledge, this is the first instance-dependent sample complexity bound for finding an NE estimate with $\varepsilon$ bias in general-dimension matrix games with noisy feedback and potentially non-unique equilibria. Our algorithm builds on recent advances in online resource allocation and operates in two stages: (1) identifying the support set of an NE, and (2) computing the unique NE restricted to this support. Both stages rely on a careful analysis of LP solutions derived from noisy samples.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An LP-Based Approach for Bilinear Saddle Point Problem with Instance-dependent Guarantee and Noisy Feedback
Jiang, Jiashuo
Zhang, Mengxiao
Optimization and Control
In this work, we study the sample complexity of obtaining a Nash equilibrium (NE) estimate in two-player zero-sum matrix games with noisy feedback. Specifically, we propose a novel algorithm that repeatedly solves linear programs (LPs) to obtain an NE estimate with bias at most $\varepsilon$ with a sample complexity of $O\left(\frac{m_1 m_2}{\varepsilon\min\{δ^2,σ_0^2,σ^3\}} \log\frac{m_1 m_2}{\varepsilon}\right)$ for general $m_1 \times m_2$ game matrices, where $σ$, $σ_0$, $δ$ are some problem-dependent constants. To our knowledge, this is the first instance-dependent sample complexity bound for finding an NE estimate with $\varepsilon$ bias in general-dimension matrix games with noisy feedback and potentially non-unique equilibria. Our algorithm builds on recent advances in online resource allocation and operates in two stages: (1) identifying the support set of an NE, and (2) computing the unique NE restricted to this support. Both stages rely on a careful analysis of LP solutions derived from noisy samples.
title An LP-Based Approach for Bilinear Saddle Point Problem with Instance-dependent Guarantee and Noisy Feedback
topic Optimization and Control
url https://arxiv.org/abs/2602.12513