OCLGPRMay 24, 2024

A Fisher-Rao gradient flow for entropic mean-field min-max games

arXiv:2405.15834v24 citationsh-index: 9Trans. Mach. Learn. Res.
Originality Incremental advance
AI Analysis

This work addresses convergence issues in min-max games for machine learning applications, but it appears incremental as it builds on existing gradient flow methods with entropy regularization.

The paper tackles the problem of solving convex-concave min-max games with entropy regularization by analyzing the convergence of a Fisher-Rao gradient flow, demonstrating explicit convergence rates to the unique mixed Nash equilibrium.

Gradient flows play a substantial role in addressing many machine learning problems. We examine the convergence in continuous-time of a \textit{Fisher-Rao} (Mean-Field Birth-Death) gradient flow in the context of solving convex-concave min-max games with entropy regularization. We propose appropriate Lyapunov functions to demonstrate convergence with explicit rates to the unique mixed Nash equilibrium.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes