Communication efficient quasi-Newton distributed optimization based on the Douglas-Rachford envelope

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Dingran, Freris, Nikolaos M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910676333625344
author Yi, Dingran
Freris, Nikolaos M.
author_facet Yi, Dingran
Freris, Nikolaos M.
contents We consider distributed optimization in the client-server setting. By use of Douglas-Rachford splitting to the dual of the sum problem, we design a BFGS method that requires minimal communication (sending/receiving one vector per round for each client). Our method is line search free and achieves superlinear convergence. Experiments are also used to demonstrate the merits in decreasing communication and computation costs.
format Preprint
id arxiv_https___arxiv_org_abs_2409_04049
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Communication efficient quasi-Newton distributed optimization based on the Douglas-Rachford envelope
Yi, Dingran
Freris, Nikolaos M.
Optimization and Control
We consider distributed optimization in the client-server setting. By use of Douglas-Rachford splitting to the dual of the sum problem, we design a BFGS method that requires minimal communication (sending/receiving one vector per round for each client). Our method is line search free and achieves superlinear convergence. Experiments are also used to demonstrate the merits in decreasing communication and computation costs.
title Communication efficient quasi-Newton distributed optimization based on the Douglas-Rachford envelope
topic Optimization and Control
url https://arxiv.org/abs/2409.04049