期刊
JOURNAL OF MATHEMATICS
卷 2021, 期 -, 页码 -出版社
HINDAWI LTD
DOI: 10.1155/2021/6115451
关键词
-
类别
资金
- Humanities and Social Science Fund of Ministry of Education of China [20YJC630202]
- Natural Science Foundation Projection of Chongqing CSTC [cstc2020jcyj-msxmX0287]
This study introduces a differentially private distributed optimization algorithm that can be implemented on time-changing unbalanced digraphs. Under general local convex objective functions, the algorithm can achieve a sublinear expected bound of regret. The results demonstrate a trade-off between optimization accuracy and privacy level.
This paper investigates a constrained distributed optimization problem enabled by differential privacy where the underlying network is time-changing with unbalanced digraphs. To solve such a problem, we first propose a differentially private online distributed algorithm by injecting adaptively adjustable Laplace noises. The proposed algorithm can not only protect the privacy of participants without compromising a trusted third party, but also be implemented on more general time-varying unbalanced digraphs. Under mild conditions, we then show that the proposed algorithm can achieve a sublinear expected bound of regret for general local convex objective functions. The result shows that there is a trade-off between the optimization accuracy and privacy level. Finally, numerical simulations are conducted to validate the efficiency of the proposed algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据