A Flexible Framework for Decentralized Composite Optimization with Compressed Communication

This paper addresses the decentralized composite optimization problem, where a network of agents cooperatively minimize the sum of their local objective functions with non-differentiable terms. We propose a novel communication-efficient decentralized ADMM framework, termed as CE-DADMM, by combining...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongyi Chang, Zhen Zhang, Shaofu Yang, Jinde Cao
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Fractal and Fractional
Subjects:
Online Access:https://www.mdpi.com/2504-3110/8/12/721
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104548143267840
author Zhongyi Chang
Zhen Zhang
Shaofu Yang
Jinde Cao
author_facet Zhongyi Chang
Zhen Zhang
Shaofu Yang
Jinde Cao
author_sort Zhongyi Chang
collection DOAJ
description This paper addresses the decentralized composite optimization problem, where a network of agents cooperatively minimize the sum of their local objective functions with non-differentiable terms. We propose a novel communication-efficient decentralized ADMM framework, termed as CE-DADMM, by combining the ADMM framework with the three-point compressed (3PC) communication mechanism. This framework not only covers existing mainstream communication-efficient algorithms but also introduces a series of new algorithms. One of the key features of the CE-DADMM framework is its flexibility, allowing it to adapt to different communication and computation needs, balancing communication efficiency and computational overhead. Notably, when employing quasi-Newton updates, CE-DADMM becomes the first communication-efficient second-order algorithm based on compression that can efficiently handle composite optimization problems. Theoretical analysis shows that, even in the presence of compression errors, the proposed algorithm maintains exact linear convergence when the local objective functions are strongly convex. Finally, numerical experiments demonstrate the algorithm’s impressive communication efficiency.
format Article
id doaj-art-1d983074f736400a98bd16ba0513a4f7
institution Kabale University
issn 2504-3110
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Fractal and Fractional
spelling doaj-art-1d983074f736400a98bd16ba0513a4f72024-12-27T14:27:07ZengMDPI AGFractal and Fractional2504-31102024-12-0181272110.3390/fractalfract8120721A Flexible Framework for Decentralized Composite Optimization with Compressed CommunicationZhongyi Chang0Zhen Zhang1Shaofu Yang2Jinde Cao3School of Computer Science and Engineering, Southeast University, Nanjing 211189, ChinaSchool of Computer Science and Engineering, Southeast University, Nanjing 211189, ChinaSchool of Computer Science and Engineering, Southeast University, Nanjing 211189, ChinaSchool of Mathematics, Southeast University, Nanjing 211189, ChinaThis paper addresses the decentralized composite optimization problem, where a network of agents cooperatively minimize the sum of their local objective functions with non-differentiable terms. We propose a novel communication-efficient decentralized ADMM framework, termed as CE-DADMM, by combining the ADMM framework with the three-point compressed (3PC) communication mechanism. This framework not only covers existing mainstream communication-efficient algorithms but also introduces a series of new algorithms. One of the key features of the CE-DADMM framework is its flexibility, allowing it to adapt to different communication and computation needs, balancing communication efficiency and computational overhead. Notably, when employing quasi-Newton updates, CE-DADMM becomes the first communication-efficient second-order algorithm based on compression that can efficiently handle composite optimization problems. Theoretical analysis shows that, even in the presence of compression errors, the proposed algorithm maintains exact linear convergence when the local objective functions are strongly convex. Finally, numerical experiments demonstrate the algorithm’s impressive communication efficiency.https://www.mdpi.com/2504-3110/8/12/721decentralized composite optimizationADMMquasi-Newtoncommunication-efficient mechanism
spellingShingle Zhongyi Chang
Zhen Zhang
Shaofu Yang
Jinde Cao
A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
Fractal and Fractional
decentralized composite optimization
ADMM
quasi-Newton
communication-efficient mechanism
title A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
title_full A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
title_fullStr A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
title_full_unstemmed A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
title_short A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
title_sort flexible framework for decentralized composite optimization with compressed communication
topic decentralized composite optimization
ADMM
quasi-Newton
communication-efficient mechanism
url https://www.mdpi.com/2504-3110/8/12/721
work_keys_str_mv AT zhongyichang aflexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT zhenzhang aflexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT shaofuyang aflexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT jindecao aflexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT zhongyichang flexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT zhenzhang flexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT shaofuyang flexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication
AT jindecao flexibleframeworkfordecentralizedcompositeoptimizationwithcompressedcommunication