Federated Minimax Optimization: Improved Convergence Analyses and Algorithms

03/09/2022
by   Pranay Sharma, et al.
11

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 order-optimal sample complexity for several classes of nonconvex-concave and nonconvex-nonconcave minimax problems, and also enjoys 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/22/2020

Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities

In this paper, we study zeroth-order algorithms for minimax optimization...
06/02/2022

A Communication-efficient Algorithm with Linear Convergence for Federated Minimax Learning

In this paper, we study a large-scale multi-agent minimax optimization p...
05/29/2021

A Federated Learning Framework for Nonconvex-PL Minimax Problems

We consider a general class of nonconvex-PL minimax problems in the cros...
06/15/2020

The Landscape of Nonconvex-Nonconcave Minimax Optimization

Minimax optimization has become a central tool for modern machine learni...
12/31/2020

Federated Nonconvex Sparse Learning

Nonconvex sparse learning plays an essential role in many areas, such as...
11/20/2018

Sampling Can Be Faster Than Optimization

Optimization algorithms and Monte Carlo sampling algorithms have provide...
03/31/2020

Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization

Rapid advances in data collection and processing capabilities have allow...