paper-with-me

Papers

Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives

2025-01-28 · Jing An, Jianfeng Lu

The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm designed to find Nash equilibria in min-max games. We analyze the two-timescale GDA by investigating the effects of learning rate ratios on convergence behavior in both finite-dimensional and mean-field settings. In particular, for finite-dimensional quadratic min-max games, we obtain long-time convergence in near quasi-static regimes through the hypocoercivity method. For mean-field GDA dynamics, we investigate convergence under a finite-scale ratio using a mixed synchronous-reflection coupling technique.

📄 PDF Abstract BibTeX arXiv:2501.17122

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation

2020-09-30 · ICLR 2021 1 · Tanner Fiez, Lillian Ratliff

We study the role that a finite timescale separation parameter $\tau$ has on gradient descent-ascent in two-player non-convex, non-concave zero-sum games where the learning rate of player 1 is denoted by $\gamma_1$ and t…

Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games

2021-12-01 · NeurIPS 2021 12 · Tanner Fiez, Lillian Ratliff, Eric Mazumdar, Evan Faulkner 외

We study gradient descent-ascent learning dynamics with timescale separation in unconstrained continuous action zero-sum games where the minimizing player faces a nonconvex optimization problem and the maximizing player …

Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games

2021-05-21 · NeurIPS 2021 12 · Tanner Fiez, Lillian J Ratliff, Eric Mazumdar, Evan Faulkner 외

We study gradient descent-ascent learning dynamics with timescale separation in unconstrained continuous action zero-sum games where the minimizing player faces a nonconvex optimization problem and the maximizing player …

Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization

2024-08-21 · Tianyi Lin, Chi Jin, Michael. I. Jordan

We provide a unified analysis of two-timescale gradient descent ascent (TTGDA) for solving structured nonconvex minimax optimization problems in the form of $\min_\textbf{x} \max_{\textbf{y} \in Y} f(\textbf{x}, \textbf{…

On the Stability and Generalization of First-order Bilevel Minimax Optimization

2026-04-22 · Xuelin Zhang, Peipei Yuan arxiv

Bilevel optimization and bilevel minimax optimization have recently emerged as unifying frameworks for a range of machine-learning tasks, including hyperparameter optimization and reinforcement learning. The existing lit…

Hyperparameter OptimizationReinforcement LearningBilevel Optimization