Federated Minimax Optimization: Improved Convergence Analyses and Algorithms

TL;DR

This paper analyzes and improves the convergence of federated minimax optimization algorithms, specifically Local SGDA, providing tighter guarantees and proposing a momentum-based method that outperforms existing algorithms.

Contribution

The paper offers a novel, tighter analysis of Local SGDA in federated minimax problems, establishing order-optimal sample complexity and linear speedup, and introduces a momentum-based algorithm with enhanced performance.

Findings

Local SGDA has order-optimal sample complexity.

The algorithms achieve linear speedup with the number of clients.

The momentum-based method outperforms Local SGDA in experiments.

Abstract

In this paper, we consider nonconvex minimax optimization, which is gaining prominence in many modern machine learning applications such as GANs. Large-scale edge-based collection of training data in these applications calls for communication-efficient distributed optimization algorithms, such as those used in federated learning, to process the data. In this paper, we analyze Local stochastic gradient descent ascent (SGDA), the local-update version of the SGDA algorithm. SGDA is the core algorithm used in minimax optimization, but it is not well-understood in a distributed setting. We prove that Local SGDA has \textit{order-optimal} sample complexity for several classes of nonconvex-concave and nonconvex-nonconcave minimax problems, and also enjoys \textit{linear speedup} with respect to the number of clients. We provide a novel and tighter analysis, which improves the convergence and communication guarantees in the existing literature. For nonconvex-PL and nonconvex-one-point-concave functions, we improve the existing complexity results for centralized minimax problems. Furthermore, we propose a momentum-based local-update algorithm, which has the same convergence guarantees, but outperforms Local SGDA as demonstrated in our experiments.