Poster

On the Suboptimality of Negative Momentum for Minimax Optimization

Guodong Zhang · Yuanhao Wang

Keywords: [ Learning Theory and Statistics ] [ Gradient-Based Optimization ]

[ Abstract ]
Tue 13 Apr 6:30 p.m. PDT — 8:30 p.m. PDT

Abstract:

Smooth game optimization has recently attracted great interest in machine learning as it generalizes the single-objective optimization paradigm. However, game dynamics is more complex due to the interaction between different players and is therefore fundamentally different from minimization, posing new challenges for algorithm design. Notably, it has been shown that negative momentum is preferred due to its ability to reduce oscillation in game dynamics. Nevertheless, existing analysis of negative momentum was restricted to simple bilinear games. In this paper, we extend the analysis to smooth and strongly-convex strongly-concave minimax games by taking the variational inequality formulation. By connecting Polyak’s momentum with Chebyshev polynomials, we show that negative momentum accelerates convergence of game dynamics locally, though with a suboptimal rate. To the best of our knowledge, this is the \emph{first work} that provides an explicit convergence rate for negative momentum in this setting.

Chat is not available.