Distributed Generalized Linear Models: A Privacy-Preserving Approach

2025/03/19 by Daniel Tinoco, Tinoco, Daniel, Raquel Menezes +3 · 1 voice
Computer Science · Mathematics · #62J12 (Primary) 68U99 (Secondary) #C.2.4 #Computation (stat.CO) #Distributed #FOS: Computer and information sciences #G.3 #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC) #cs.DC #stat.CO

paper · pdf · doi:10.48550/arxiv.2503.15287

openalex publication_date 2025/03/19 · arxiv published 2025/03/19 · arxiv updated 2025/03/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a novel approach to classical linear regression, enabling model computation from data streams or in a distributed setting while preserving data privacy in federated environments. We extend this framework to generalized linear models (GLMs), ensuring scalability and adaptability to diverse data distributions while maintaining privacy-preserving properties. To assess the effectiveness of our approach, we conduct numerical studies on both simulated and real datasets, comparing our method with conventional maximum likelihood estimation for GLMs using iteratively reweighted least squares. Our results demonstrate the advantages of the proposed method in distributed and federated settings.

Discussions

• New paper under submission, in the confluence of statistics and distributed systems. arxiv.org/abs/2503.15287 [bsky, 3 points, 0 comments]

Related

• Differentially Private Bayesian Inference for Generalized Linear Models
• The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds
• Logistics Regression Model for Differentially-Private Matrix Masked Data
• Privacy-Preserving Generalized Linear Models using Distributed Block Coordinate Descent
• Privacy-Preserving and Lossless Distributed Estimation of High-Dimensional Generalized Additive Mixed Models