Differentially-Private Collaborative Online Personalized Mean Estimation
Document Type
Conference Proceeding
Publication Date
1-1-2023
Abstract
We consider the problem of collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific distributions. In particular, we provide a method based on hypothesis testing coupled with differential privacy. Two privacy mechanisms are proposed and we provide a theoretical convergence analysis of the proposed algorithm for any bounded unknown distributions on the agents' data. Numerical results show that for a considered scenario the proposed approach converges much faster than a fully local approach where agents do not share data, and performs comparably to ideal performance where all data is public. This illustrates the benefit of private collaboration in an online setting.
Identifier
85171432465 (Scopus)
ISBN
[9781665475549]
Publication Title
IEEE International Symposium on Information Theory Proceedings
External Full Text Location
https://doi.org/10.1109/ISIT54713.2023.10206796
ISSN
21578095
First Page
737
Last Page
742
Volume
2023-June
Grant
1815322
Fund Ref
National Science Foundation
Recommended Citation
Yakimenka, Yauhen; Weng, Chung Wei; Lin, Hsuan Yin; Rosnes, Eirik; and Kliewer, Jörg, "Differentially-Private Collaborative Online Personalized Mean Estimation" (2023). Faculty Publications. 2204.
https://digitalcommons.njit.edu/fac_pubs/2204