A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems

TL;DR

This paper introduces a decentralized adaptive momentum algorithm, DADAM$^3$, for solving min-max optimization problems, especially in settings like GAN training, where communication constraints and privacy are critical, demonstrating superior empirical performance.

Contribution

It proposes a novel decentralized adaptive momentum method for min-max problems under Minty Variational Inequality conditions, addressing practical limitations of existing algorithms.

Findings

DADAM$^3$ achieves faster convergence rates.

The method outperforms existing decentralized algorithms in experiments.

Effective in training GANs with decentralized data.

Abstract

Min-max saddle point games have recently been intensely studied, due to their wide range of applications, including training Generative Adversarial Networks (GANs). However, most of the recent efforts for solving them are limited to special regimes such as convex-concave games. Further, it is customarily assumed that the underlying optimization problem is solved either by a single machine or in the case of multiple machines connected in centralized fashion, wherein each one communicates with a central node. The latter approach becomes challenging, when the underlying communications network has low bandwidth. In addition, privacy considerations may dictate that certain nodes can communicate with a subset of other nodes. Hence, it is of interest to develop methods that solve min-max games in a decentralized manner. To that end, we develop a decentralized adaptive momentum (ADAM)-type algorithm for solving min-max optimization problem under the condition that the objective function satisfies a Minty Variational Inequality condition, which is a generalization to convex-concave case. The proposed method overcomes shortcomings of recent non-adaptive gradient-based decentralized algorithms for min-max optimization problems that do not perform well in practice and require careful tuning. In this paper, we obtain non-asymptotic rates of convergence of the proposed algorithm (coined DADAM$^3$) for finding a (stochastic) first-order Nash equilibrium point and subsequently evaluate its performance on training GANs. The extensive empirical evaluation shows that DADAM$^3$ outperforms recently developed methods, including decentralized optimistic stochastic gradient for solving such min-max problems.