Decentralized Conjugate Gradient and Memoryless BFGS Methods

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Liping, Wu, Hao, Zhang, Hongchao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917894383730688
author Wang, Liping
Wu, Hao
Zhang, Hongchao
author_facet Wang, Liping
Wu, Hao
Zhang, Hongchao
contents This paper proposes a new decentralized conjugate gradient (NDCG) method and a decentralized memoryless BFGS (DMBFGS) method for the nonconvex and strongly convex decentralized optimization problem, respectively, of minimizing a finite sum of continuously differentiable functions over a fixed-connected undirected network. Gradient tracking techniques are applied in these two methods to enhance their convergence properties and the numerical stability. In particular, we show global convergence of NDCG with constant stepsize for general nonconvex smooth decentralized optimization. Our new DMBFGS method uses a scaled memoryless BFGS technique and only requires gradient information to approximate second-order information of the component functions in the objective. We also establish global convergence and linear convergence rate of DMBFGS with constant stepsize for strongly convex smooth decentralized optimization. Our numerical results show that NDCG and DMBFGS are very efficient in terms of both iteration and communication cost compared with other state-of-the-art methods for solving smooth decentralized optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2409_07122
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decentralized Conjugate Gradient and Memoryless BFGS Methods
Wang, Liping
Wu, Hao
Zhang, Hongchao
Optimization and Control
This paper proposes a new decentralized conjugate gradient (NDCG) method and a decentralized memoryless BFGS (DMBFGS) method for the nonconvex and strongly convex decentralized optimization problem, respectively, of minimizing a finite sum of continuously differentiable functions over a fixed-connected undirected network. Gradient tracking techniques are applied in these two methods to enhance their convergence properties and the numerical stability. In particular, we show global convergence of NDCG with constant stepsize for general nonconvex smooth decentralized optimization. Our new DMBFGS method uses a scaled memoryless BFGS technique and only requires gradient information to approximate second-order information of the component functions in the objective. We also establish global convergence and linear convergence rate of DMBFGS with constant stepsize for strongly convex smooth decentralized optimization. Our numerical results show that NDCG and DMBFGS are very efficient in terms of both iteration and communication cost compared with other state-of-the-art methods for solving smooth decentralized optimization.
title Decentralized Conjugate Gradient and Memoryless BFGS Methods
topic Optimization and Control
url https://arxiv.org/abs/2409.07122