Skip to main navigation Skip to search Skip to main content

Communication-Constrained Private Decentralized Online Personalized Mean Estimation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider the problem of communication-constrained collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific distributions. A consensus-based algorithm is studied under the framework of differential privacy in order to protect each agent's data. We give a theoretical convergence analysis of the proposed consensus-based algorithm for any bounded unknown distributions on the agents' data, showing that collaboration provides faster convergence than a fully local approach where agents do not share data, under an oracle decision rule and under some restrictions on the privacy level and the agents' connectivity, which illustrates the benefit of private collaboration in an online setting under a communication restriction on the agents. The theoretical faster-than-local convergence guarantee is backed up by several numerical results.

Original languageEnglish (US)
Title of host publication2025 IEEE Information Theory Workshop, ITW 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331531423
DOIs
StatePublished - 2025
Event2025 IEEE Information Theory Workshop, ITW 2025 - Sydney, Australia
Duration: Sep 29 2025Oct 3 2025

Publication series

Name2025 IEEE Information Theory Workshop, ITW 2025

Conference

Conference2025 IEEE Information Theory Workshop, ITW 2025
Country/TerritoryAustralia
CitySydney
Period9/29/2510/3/25

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Information Systems
  • Signal Processing
  • Theoretical Computer Science

Fingerprint

Dive into the research topics of 'Communication-Constrained Private Decentralized Online Personalized Mean Estimation'. Together they form a unique fingerprint.

Cite this