Federated Minimax Optimization: Improved Convergence Analyses and Algorithms

PRANAY SHARMA · Rohan Panda · Gauri Joshi · Pramod K Varshney

Hall E #605

Keywords: [ T: Optimization ] [ OPT: First-order ] [ OPT: Non-Convex ] [ DL: Generative Models and Autoencoders ] [ OPT: Stochastic ] [ OPT: Large Scale, Parallel and Distributed ] [ DL: Robustness ] [ Optimization ]


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.

Chat is not available.