Differentially Private Distributed Online Algorithms over Time-Varying Directed Networks

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

69 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)4-17
Journal / PublicationIEEE Transactions on Signal and Information Processing over Networks
Volume4
Issue number1
Publication statusPublished - 1 Mar 2018
Externally publishedYes

Abstract

We consider a private distributed online optimization problem where a set of agents aim to minimize the sum of locally convex cost functions while each desires that the local cost function of individual agent is kept differentially private. To solve such problem, we propose differentially private distributed stochastic subgradient online optimization algorithm over time-varying directed networks. We use differential privacy to preserve the privacy of participating agents. We show that our algorithm preserves differential privacy and achieves logarithmic expected regret under locally strong convexity. Moreover, we also show that square-root expected regret is obtained under local convexity. Furthermore, we reveal the tradeoff between the privacy level and the performance of our algorithm.

Research Area(s)

  • differential privacy, expected regret, Private distributed online optimization, time-varying directed networks

Bibliographic Note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to lbscholars@cityu.edu.hk.