MultiLRSGA: A method for multi-player differentiable games

TL;DR

MultiLRSGA is a novel method extending LRSGA to multi-player differentiable games, utilizing Jacobian decomposition and low-rank approximations to compute stable Nash equilibria with proven local convergence.

Contribution

It introduces a multi-player extension of LRSGA that employs block antisymmetric corrections and low-rank Jacobian approximations for stable equilibrium computation.

Findings

Proves local linear convergence under standard assumptions.

Extends convergence analysis from two-player to multi-player games.

Maintains computational efficiency with low-rank symplectic corrections.

Abstract

We propose MultiLRSGA, an $h$-player extension of LRSGA for the computation of stable Nash equilibria in differentiable games. The method originates from the decomposition of the game Jacobian into symmetric and antisymmetric components, which motivates symplectic corrections designed to attenuate the rotational part of the dynamics. In the two-player setting, LRSGA replaces mixed second-order blocks with low-rank secant approximations. The passage to the multi-player case, however, is not a mere blockwise reformulation: the antisymmetric correction is no longer determined by a single pair of cross-interactions, but by a block antisymmetric operator collecting all pairwise couplings among the players. On this basis, we formulate MultiLRSGA by constructing, for each player, a low-rank approximation of the Jacobian of the partial gradient and extracting from it the blocks required to define an approximate antisymmetric correction. Under standard local assumptions around a stable Nash equilibrium, we prove local linear convergence of the method. The key technical ingredient is a lemma controlling the distance between the exact antisymmetric correction and its secant approximation in the $h$-player setting, thereby extending to the multi-player framework the convergence mechanism previously available for LRSGA. The proposed formulation preserves the computational advantages of low-rank symplectic corrections and is naturally suited to numerical validation on differentiable games with explicit payoffs and more than two agents.