Iteratively Regularized Gradient Tracking Methods for Optimal Equilibrium Seeking

TL;DR

This paper introduces novel single-timescale distributed gradient tracking algorithms for finding optimal Nash equilibria in networked noncooperative games, improving scalability and convergence guarantees over traditional methods.

Contribution

It develops and analyzes the first single-timescale regularized gradient tracking methods for optimal NE seeking, applicable to directed and stochastic undirected networks.

Findings

Algorithms converge to the optimal NE.

New convergence rates for consensus error.

Preliminary numerical validation on Nash-Cournot game.

Abstract

In noncooperative Nash games, equilibria are often inefficient. This is exemplified by the Prisoner's Dilemma and was first provably shown in the 1980s. Since then, understanding the quality of Nash equilibrium (NE) received considerable attention, leading to the emergence of inefficiency measures characterized by the best or the worst equilibrium. Traditionally, computing an optimal NE in monotone regimes is done through two-loop schemes which lack scalability and provable performance guarantees. The goal in this work lies in the development of among the first single-timescale distributed gradient tracking optimization methods for optimal NE seeking over networks. Our main contributions are as follows. By employing a regularization-based relaxation approach within two existing distributed gradient tracking methods, namely Push-Pull and DSGT, we devise and analyze two single-timescale iteratively regularized gradient tracking algorithms. The first method addresses computing the optimal NE over directed networks, while the second method addresses a stochastic variant of this problem over undirected networks. For both methods, we establish the convergence to the optimal NE and derive new convergence rate statements for the consensus error of the generated iterates. We provide preliminary numerical results on a Nash-Cournot game.