Privacy Preservation in Distributed Subgradient Optimization Algorithms

doi:10.1109/TCYB.2017.2728644

CSpace > 系统科学研究所

	Privacy Preservation in Distributed Subgradient Optimization Algorithms
	Lou, Youcheng 1,2; Yu, Lean 3; Wang, Shouyang2 ; Yi, Peng 4
	2018-07-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	48 期号:7 页码:2154-2165
摘要	In this paper, some privacy-preserving features for distributed subgradient optimization algorithms are considered. Most of the existing distributed algorithms focus mainly on the algorithm design and convergence analysis, but not the protection of agents' privacy. Privacy is becoming an increasingly important issue in applications involving sensitive information. In this paper, we first show that the distributed subgradient synchronous homogeneous-stepsize algorithm is not privacy preserving in the sense that the malicious agent can asymptotically discover other agents' subgradients by transmitting untrue estimates to its neighbors. Then a distributed subgradient asynchronous heterogeneous-stepsize projection algorithm is proposed and accordingly its convergence and optimality is established. In contrast to the synchronous homogeneous-stepsize algorithm, in the new algorithm agents make their optimization updates asynchronously with heterogeneous stepsizes. The introduced two mechanisms of projection operation and asynchronous heterogeneous-stepsize optimization can guarantee that agents' privacy can be effectively protected.
关键词	Asynchronous optimization distributed optimization heterogeneous-stepsize privacy preservation
DOI	10.1109/TCYB.2017.2728644
语种	英语
资助项目	Key Program of National Natural Science Foundation of China[71433001] ; Key Program of National Natural Science Foundation of China[71631005] ; National Natural Science Foundation of China[71401163] ; Hong Kong Scholars Program[XJ2015049] ; National Program for Support of Top-Notch Young Professionals
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000435342100017
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/30483
专题	系统科学研究所
通讯作者	Yu, Lean
作者单位	1.Chinese Univ Hong Kong, Dept Syst Engn & Engn Management, Hong Kong, Hong Kong, Peoples R China 2.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China 3.Beijing Univ Chem Technol, Sch Econ & Management, Beijing 100029, Peoples R China 4.Univ Toronto, Dept Elect & Comp Engn, Toronto, ON M5S 3G4, Canada
推荐引用方式 GB/T 7714	Lou, Youcheng,Yu, Lean,Wang, Shouyang,et al. Privacy Preservation in Distributed Subgradient Optimization Algorithms[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(7):2154-2165.
APA	Lou, Youcheng,Yu, Lean,Wang, Shouyang,&Yi, Peng.(2018).Privacy Preservation in Distributed Subgradient Optimization Algorithms.IEEE TRANSACTIONS ON CYBERNETICS,48(7),2154-2165.
MLA	Lou, Youcheng,et al."Privacy Preservation in Distributed Subgradient Optimization Algorithms".IEEE TRANSACTIONS ON CYBERNETICS 48.7(2018):2154-2165.