Journal
JOURNAL OF MATHEMATICS
Volume 2021, Issue -, Pages -Publisher
HINDAWI LTD
DOI: 10.1155/2021/6115451
Keywords
-
Categories
Funding
- Humanities and Social Science Fund of Ministry of Education of China [20YJC630202]
- Natural Science Foundation Projection of Chongqing CSTC [cstc2020jcyj-msxmX0287]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available