A Zeroth-Order Proximal Algorithm for Consensus Optimization

doi:10.1109/CDC56724.2024.10886308

	A Zeroth-Order Proximal Algorithm for Consensus Optimization
	Wang, Chengan; Ou, Zichong; Lu, Jie
	2024
会议录名称	PROCEEDINGS OF THE IEEE CONFERENCE ON DECISION AND CONTROL ; 63RD IEEE CONFERENCE ON DECISION AND CONTROL, CDC 2024
ISSN	0743-1546
页码	3115-3120
DOI	10.1109/CDC56724.2024.10886308
摘要	This paper considers a consensus optimization problem, where all the nodes in a network, with access to the zeroth-order information of its local objective function only, attempt to cooperatively achieve a common minimizer of the sum of their local objectives. To address this problem, we develop ZoPro, a zeroth-order proximal algorithm, which incorporates a zeroth-order oracle for approximating Hessian and gradient into a recently proposed, high-performance distributed secondorder proximal algorithm. We show that the proposed ZoPro algorithm, equipped with a dynamic stepsize, converges linearly to a neighborhood of the optimum in expectation, provided that each local objective function is strongly convex and smooth. Extensive simulations demonstrate that ZoPro converges faster than several state-of-the-art distributed zeroth-order algorithms and outperforms a few distributed second-order algorithms in terms of running time for reaching given accuracy. © 2024 IEEE.
会议录编者/会议主办者	Advanced Technologies for Human-Centered Medicine (Anthem) ; et al. ; Mathworks ; Mitsubishi Electric ; MOST Centro Nazionale per la Mobilita Sostenibile ; Quanser
关键词	Optimization algorithms Extensive simulations Neighbourhood Objective functions Optimisations Optimization problems Performance Proximal algorithm Second orders Simulation demonstrate Step size
会议名称	63rd IEEE Conference on Decision and Control, CDC 2024
会议地点	Milan, Italy
会议日期	December 16, 2024 - December 19, 2024
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20251118040385
EI主题词	Consensus algorithm
EISSN	2576-2370
EI分类号	1103.3 Data Communication, Equipment and Techniques ; 1105.3 Blockchain Technology ; 1106.1 Computer Programming ; 1201.7 Optimization Techniques
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/503676
专题	信息科学与技术学院信息科学与技术学院_PI研究组_陆疌组信息科学与技术学院_硕士生信息科学与技术学院_博士生
通讯作者	Wang, Chengan
作者单位	ShanghaiTech University, School of Information Science and Technology, Shanghai; 201210, China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Wang, Chengan,Ou, Zichong,Lu, Jie. A Zeroth-Order Proximal Algorithm for Consensus Optimization[C]//Advanced Technologies for Human-Centered Medicine (Anthem), et al., Mathworks, Mitsubishi Electric, MOST Centro Nazionale per la Mobilita Sostenibile, Quanser:Institute of Electrical and Electronics Engineers Inc.,2024:3115-3120.