From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning

Authors: Edwige Cyffers, Aurélien Bellet, Debabrota Basu
Published: 2023-02-24 | Updated: 2023-07-12

Source: https://arxiv.org/abs/2302.12559

PDF: https://arxiv.org/pdf/2302.12559

Labels Predicted by AI

プライバシー保護技術 固定点反復法 収束分析

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

We study differentially private (DP) machine learning algorithms as instances of noisy fixed-point iterations, in order to derive privacy and utility results from this well-studied framework. We show that this new perspective recovers popular private gradient-based methods like DP-SGD and provides a principled way to design and analyze new private optimization algorithms in a flexible manner. Focusing on the widely-used Alternating Directions Method of Multipliers (ADMM) method, we use our general framework to derive novel private ADMM algorithms for centralized, federated and fully decentralized learning. For these three algorithms, we establish strong privacy guarantees leveraging privacy amplification by iteration and by subsampling. Finally, we provide utility guarantees using a unified analysis that exploits a recent linear convergence result for noisy fixed-point iterations.