Adaptive Federated Minimax Optimization with Lower Complexities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Feihu, Wang, Xinrui, Li, Junyi, Chen, Songcan
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909122945875968
author Huang, Feihu
Wang, Xinrui
Li, Junyi
Chen, Songcan
author_facet Huang, Feihu
Wang, Xinrui
Li, Junyi
Chen, Songcan
contents Federated learning is a popular distributed and privacy-preserving learning paradigm in machine learning. Recently, some federated learning algorithms have been proposed to solve the distributed minimax problems. However, these federated minimax algorithms still suffer from high gradient or communication complexity. Meanwhile, few algorithm focuses on using adaptive learning rate to accelerate these algorithms. To fill this gap, in the paper, we study a class of nonconvex minimax optimization, and propose an efficient adaptive federated minimax optimization algorithm (i.e., AdaFGDA) to solve these distributed minimax problems. Specifically, our AdaFGDA builds on the momentum-based variance reduced and local-SGD techniques, and it can flexibly incorporate various adaptive learning rates by using the unified adaptive matrices. Theoretically, we provide a solid convergence analysis framework for our AdaFGDA algorithm under non-i.i.d. setting. Moreover, we prove our AdaFGDA algorithm obtains a lower gradient (i.e., stochastic first-order oracle, SFO) complexity of $\tilde{O}(ε^{-3})$ with lower communication complexity of $\tilde{O}(ε^{-2})$ in finding $ε$-stationary point of the nonconvex minimax problems. Experimentally, we conduct some experiments on the deep AUC maximization and robust neural network training tasks to verify efficiency of our algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2211_07303
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Adaptive Federated Minimax Optimization with Lower Complexities
Huang, Feihu
Wang, Xinrui
Li, Junyi
Chen, Songcan
Machine Learning
Optimization and Control
Federated learning is a popular distributed and privacy-preserving learning paradigm in machine learning. Recently, some federated learning algorithms have been proposed to solve the distributed minimax problems. However, these federated minimax algorithms still suffer from high gradient or communication complexity. Meanwhile, few algorithm focuses on using adaptive learning rate to accelerate these algorithms. To fill this gap, in the paper, we study a class of nonconvex minimax optimization, and propose an efficient adaptive federated minimax optimization algorithm (i.e., AdaFGDA) to solve these distributed minimax problems. Specifically, our AdaFGDA builds on the momentum-based variance reduced and local-SGD techniques, and it can flexibly incorporate various adaptive learning rates by using the unified adaptive matrices. Theoretically, we provide a solid convergence analysis framework for our AdaFGDA algorithm under non-i.i.d. setting. Moreover, we prove our AdaFGDA algorithm obtains a lower gradient (i.e., stochastic first-order oracle, SFO) complexity of $\tilde{O}(ε^{-3})$ with lower communication complexity of $\tilde{O}(ε^{-2})$ in finding $ε$-stationary point of the nonconvex minimax problems. Experimentally, we conduct some experiments on the deep AUC maximization and robust neural network training tasks to verify efficiency of our algorithms.
title Adaptive Federated Minimax Optimization with Lower Complexities
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2211.07303