Median-of-Means for Nash Equilibrium Seeking in Heavy-Tailed Games

TL;DR

This paper introduces a Median-of-Means approach for Nash equilibrium seeking in stochastic games with heavy-tailed noise, providing robust convergence guarantees without needing preset thresholds.

Contribution

It applies Median-of-Means to Nash equilibrium algorithms, handling heavy-tailed noise and malicious attacks, with proven convergence and bias correction strategies.

Findings

Proves almost sure convergence of the proposed algorithm.

Demonstrates robustness against heavy-tailed noise and malicious attacks.

Shows effectiveness through simulation results.

Abstract

This paper studies the Nash equilibrium seeking problem for stochastic games under heavy-tailed noise. The gradient noise is considered to have a finite $\delta$-th moment ($1<\delta\le 2$), which generalizes the Gaussian noise and covers cases with infinite variance. In this work, we employ the classic method Median-of-Means (MoM) in robust estimation. MoM works by dividing samples into blocks, taking the average of each block, and then taking the median of these block averages, achieving a breakdown point of up to $1/2$. This makes the final estimate reliable even when some samples are very noisy or wrong, and thus is effective to handle the heavy-tailed noise. The method also naturally defends against malicious gradient attacks. Compared with gradient clipping, which is the most popular method to deal with the heavy-tailed noise, MoM requires no preset clipping threshold and is insensitive to the tail behavior of the noise. Under standard assumptions, we prove the almost sure convergence of the algorithm and derive its almost sure convergence rate. To address the systematic bias caused by asymmetric noise, we further design an online bias correction strategy. Simulation results show the effectiveness and efficiency of the proposed algorithms.