Differentially private distributed algorithms for stochastic aggregative games

doi:10.1016/j.automatica.2022.110440

	Differentially private distributed algorithms for stochastic aggregative games
	Wang, Jimin 1; Zhang, Ji-Feng 2,3; He, Xingkang 4
刊名	AUTOMATICA
	2022-08-01
卷号	142 页码:13
关键词	Differential privacy Stochastic aggregative games Distributed algorithms Stochastic approximation
ISSN号	0005-1098
DOI	10.1016/j.automatica.2022.110440
英文摘要	Designing privacy-preserving distributed algorithms for stochastic aggregative games is urgent due to the privacy issues caused by information exchange between players. This paper proposes two differentially private distributed algorithms seeking the Nash equilibrium in stochastic aggregative games. By adding time-varying random noises, the input and output-perturbation methods are given to protect each player's sensitive information. For the case of output-perturbation, utilizing mini-batch methods, the algorithm's mean square error is inversely proportional to the privacy level E and the number of samples. For the case of input-perturbation, a differentially private distributed stochastic approximation-type algorithm is developed to achieve almost sure convergence and (epsilon, delta)-differential privacy. Under suitable consensus time conditions, the algorithm's convergence rate is rigorously presented for the first time, where the optimal convergence rate O(1/k) in a mean square sense is obtained. Then, utilizing mini-batch methods, the influence of added privacy noise on the algorithm's performance is reduced, and the convergence rate of the algorithm is improved. Specifically, when the batch sizes and the number of consensus times at each iteration grow at a suitable rate, an exponential rate of convergence can be achieved with the same privacy level. Finally, a simulation example demonstrates the algorithms' effectiveness. (C) 2022 Elsevier Ltd. All rights reserved.
资助项目	National Key R&D Program of China[2018YFA0703800] ; National Natural Science Foundation of China[61877057]
WOS研究方向	Automation & Control Systems ; Engineering
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000833420300004
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/61118]
专题	中国科学院数学与系统科学研究院
通讯作者	Zhang, Ji-Feng
作者单位	1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Acad Math & Syst Sci, Inst Syst Sci, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China 4.Univ Notre Dame, Dept Elect Engn, Notre Dame, IN 46556 USA
推荐引用方式 GB/T 7714	Wang, Jimin,Zhang, Ji-Feng,He, Xingkang. Differentially private distributed algorithms for stochastic aggregative games[J]. AUTOMATICA,2022,142:13.
APA	Wang, Jimin,Zhang, Ji-Feng,&He, Xingkang.(2022).Differentially private distributed algorithms for stochastic aggregative games.AUTOMATICA,142,13.
MLA	Wang, Jimin,et al."Differentially private distributed algorithms for stochastic aggregative games".AUTOMATICA 142(2022):13.