Saved in:
Bibliographic Details
Main Authors: Salgia, Sudeep, Pavlovic, Nikola, Chi, Yuejie, Zhao, Qing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.03222
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929660996091904
author Salgia, Sudeep
Pavlovic, Nikola
Chi, Yuejie
Zhao, Qing
author_facet Salgia, Sudeep
Pavlovic, Nikola
Chi, Yuejie
Zhao, Qing
contents We consider the problem of differentially private stochastic convex optimization (DP-SCO) in a distributed setting with $M$ clients, where each of them has a local dataset of $N$ i.i.d. data samples from an underlying data distribution. The objective is to design an algorithm to minimize a convex population loss using a collaborative effort across $M$ clients, while ensuring the privacy of the local datasets. In this work, we investigate the accuracy-communication-privacy trade-off for this problem. We establish matching converse and achievability results using a novel lower bound and a new algorithm for distributed DP-SCO based on Vaidya's plane cutting method. Thus, our results provide a complete characterization of the accuracy-communication-privacy trade-off for DP-SCO in the distributed setting.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03222
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
Salgia, Sudeep
Pavlovic, Nikola
Chi, Yuejie
Zhao, Qing
Machine Learning
Information Theory
We consider the problem of differentially private stochastic convex optimization (DP-SCO) in a distributed setting with $M$ clients, where each of them has a local dataset of $N$ i.i.d. data samples from an underlying data distribution. The objective is to design an algorithm to minimize a convex population loss using a collaborative effort across $M$ clients, while ensuring the privacy of the local datasets. In this work, we investigate the accuracy-communication-privacy trade-off for this problem. We establish matching converse and achievability results using a novel lower bound and a new algorithm for distributed DP-SCO based on Vaidya's plane cutting method. Thus, our results provide a complete characterization of the accuracy-communication-privacy trade-off for DP-SCO in the distributed setting.
title Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2501.03222