On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach

ICLR 2020  ·  Yuanhao Wang, Guodong Zhang, Jimmy Ba ·

Many tasks in modern machine learning can be formulated as finding equilibria in \emph{sequential} games. In particular, two-player zero-sum sequential games, also known as minimax optimization, have received growing interest. It is tempting to apply gradient descent to solve minimax optimization given its popularity and success in supervised learning. However, it has been noted that naive application of gradient descent fails to find some local minimax and can converge to non-local-minimax points. In this paper, we propose \emph{Follow-the-Ridge} (FR), a novel algorithm that provably converges to and only converges to local minimax. We show theoretically that the algorithm addresses the notorious rotational behaviour of gradient dynamics, and is compatible with preconditioning and \emph{positive} momentum. Empirically, FR solves toy minimax problems and improves the convergence of GAN training compared to the recent minimax optimization algorithms.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract
No code implementations yet. Submit your code now



Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.