Locally Differentially Private Online Federated Learning With Correlated Noise

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiaojiao, Zhu, Linglingzhi, Fay, Dominik, Johansson, Mikael
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912270541389824
author Zhang, Jiaojiao
Zhu, Linglingzhi
Fay, Dominik
Johansson, Mikael
author_facet Zhang, Jiaojiao
Zhu, Linglingzhi
Fay, Dominik
Johansson, Mikael
contents We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correlated noise and local updates with streaming non-IID data, we develop a perturbed iterate analysis that controls the impact of the noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed for several classes of nonconvex loss functions. Subject to an $(ε,δ)$-LDP budget, we establish a dynamic regret bound that quantifies the impact of key parameters and the intensity of changes in the dynamic environment on the learning performance. Numerical experiments confirm the efficacy of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18752
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Locally Differentially Private Online Federated Learning With Correlated Noise
Zhang, Jiaojiao
Zhu, Linglingzhi
Fay, Dominik
Johansson, Mikael
Machine Learning
Distributed, Parallel, and Cluster Computing
We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correlated noise and local updates with streaming non-IID data, we develop a perturbed iterate analysis that controls the impact of the noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed for several classes of nonconvex loss functions. Subject to an $(ε,δ)$-LDP budget, we establish a dynamic regret bound that quantifies the impact of key parameters and the intensity of changes in the dynamic environment on the learning performance. Numerical experiments confirm the efficacy of the proposed algorithm.
title Locally Differentially Private Online Federated Learning With Correlated Noise
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2411.18752