中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Gradient-free algorithms for distributed online convex optimization

文献类型:期刊论文

作者Liu, Yuhang1,2; Zhao, Wenxiao1,2,4; Dong, Daoyi3
刊名ASIAN JOURNAL OF CONTROL
出版日期2022-12-04
页码18
关键词distributed algorithm gradient-free algorithm multiagent system online convex optimization
ISSN号1561-8625
DOI10.1002/asjc.2996
英文摘要In this paper, we consider the distributed bandit convex optimization of time-varying objective functions over a network. By introducing perturbations into the objective functions, we design a deterministic difference and a randomized difference to replace the gradient information of the objective functions and propose two classes of gradient-free distributed algorithms. We prove that both the two classes of algorithms achieve regrets of O(T3/4)$$ O\left({T}<^>{3/4}\right) $$ for convex objective functions and O(T2/3)$$ O\left({T}<^>{2/3}\right) $$ for strongly convex objective functions, with respect to the time index T$$ T $$ and consensus of the estimates established as well. Simulation examples are given justifying the theoretical results.
WOS研究方向Automation & Control Systems
语种英语
WOS记录号WOS:000896709200001
出版者WILEY
源URL[http://ir.amss.ac.cn/handle/2S8OKBNM/60540]  
专题中国科学院数学与系统科学研究院
通讯作者Zhao, Wenxiao
作者单位1.Chinese Acad Sci, Acad Math & Syst Sci, Key Lab Syst & Control, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Math Sci, Beijing, Peoples R China
3.Univ New South Wales, Sch Engn & Informat Technol, Canberra, ACT, Australia
4.Chinese Acad Sci, Acad Math & Syst Sci, Key Lab Syst & Control, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Liu, Yuhang,Zhao, Wenxiao,Dong, Daoyi. Gradient-free algorithms for distributed online convex optimization[J]. ASIAN JOURNAL OF CONTROL,2022:18.
APA Liu, Yuhang,Zhao, Wenxiao,&Dong, Daoyi.(2022).Gradient-free algorithms for distributed online convex optimization.ASIAN JOURNAL OF CONTROL,18.
MLA Liu, Yuhang,et al."Gradient-free algorithms for distributed online convex optimization".ASIAN JOURNAL OF CONTROL (2022):18.

入库方式: OAI收割

来源:数学与系统科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。