A Mixing-Accelerated Primal-Dual Proximal Algorithm for Distributed Nonconvex Optimization

doi:10.23919/ACC60939.2024.10644289

	A Mixing-Accelerated Primal-Dual Proximal Algorithm for Distributed Nonconvex Optimization
	Zichong, O.2 ; Qiu, Chenyang 1; Wang, Dandan2 ; Jie, L.2,3
	2024
会议录名称	PROCEEDINGS OF THE AMERICAN CONTROL CONFERENCE
ISSN	0743-1619
页码	167-172
发表状态	已发表
DOI	10.23919/ACC60939.2024.10644289
摘要	In this paper, we develop a distributed mixing-accelerated primal-dual proximal algorithm, referred to as MAP-Pro, which enables nodes in multi-agent networks to cooperatively minimize the sum of their nonconvex, smooth local cost functions in a decentralized fashion. The proposed algorithm is constructed upon minimizing a computationally inexpensive augmented-Lagrangian-like function and incorporating a time-varying mixing polynomial to expedite information fusion across the network. The convergence results derived for MAP-Pro include a sublinear rate of convergence to a stationary solution and, under the Polyak-Lojasiewics (P-L) condition, a linear rate of convergence to the global optimal solution. Additionally, we may embed the well-noted Chebyshev acceleration scheme in MAP-Pro, which generates a specific sequence of mixing polynomials with given degrees and enhances the convergence performance based on MAP-Pro. Finally, we illustrate the competitive convergence speed and communication efficiency of MAP-Pro via a numerical example. © 2024 AACC.
会议录编者/会议主办者	Boeing ; Elsevier ; et al. ; Halliburton ; MathWorks ; Mitsubishi Electric Research Laboratories (MERL)
关键词	Chebyshev polynomials Clutter (information theory) Data fusion Information fusion Lagrange multipliers Optimal systems Polynomials Augmented Lagrangians Cost-function Decentralised Distributed mixing Multiagent networks Nonconvex Nonconvex optimization Nonconvex-optimization Primal-dual Proximal algorithm
会议名称	2024 American Control Conference, ACC 2024
会议地点	Toronto, ON, Canada
会议日期	July 10, 2024 - July 12, 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	20243917086375
EI主题词	Cost functions
EI分类号	1106.2 ; 1201.1 ; 1201.2 ; 1201.7 ; 1201.9 ; 716.1 Information Theory and Signal Processing ; 903.1 Information Sources and Analysis ; 961 Systems Science
原始文献类型	Conference article (CA)
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/430537
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_博士生
作者单位	1.University of Virginia, Charles L. Brown Department of Electrical and Computer Engineering, Charlottesville; VA; 22904-4743, United States 2.School of Information Science and Technology, Shanghaitech University, Shanghai; 2012, China 3.Shanghai Engineering Research Center of Energy Efficient and Custon Ai Ic, Shanghai; 201210, China
第一作者单位	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	Zichong, O.,Qiu, Chenyang,Wang, Dandan,et al. A Mixing-Accelerated Primal-Dual Proximal Algorithm for Distributed Nonconvex Optimization[C]//Boeing, Elsevier, et al., Halliburton, MathWorks, Mitsubishi Electric Research Laboratories (MERL):Institute of Electrical and Electronics Engineers Inc.,2024:167-172.