Sharp Gaussian approximations for Decentralized Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bonnerjee, Soham, Karmakar, Sayar, Wu, Wei Biao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917465412337664
author Bonnerjee, Soham
Karmakar, Sayar
Wu, Wei Biao
author_facet Bonnerjee, Soham
Karmakar, Sayar
Wu, Wei Biao
contents Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, asymptotic statistical guarantees beyond convergence remain limited. In this paper, we present two generalized Gaussian approximation results for local SGD and explore their implications. First, we prove a Berry-Esseen theorem for the final local SGD iterates, enabling valid multiplier bootstrap procedures. Second, motivated by robustness considerations, we introduce two distinct time-uniform Gaussian approximations for the entire trajectory of local SGD. The time-uniform approximations support Gaussian bootstrap-based tests for detecting adversarial attacks. Extensive simulations are provided to support our theoretical results.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sharp Gaussian approximations for Decentralized Federated Learning
Bonnerjee, Soham
Karmakar, Sayar
Wu, Wei Biao
Machine Learning
Statistics Theory
Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, asymptotic statistical guarantees beyond convergence remain limited. In this paper, we present two generalized Gaussian approximation results for local SGD and explore their implications. First, we prove a Berry-Esseen theorem for the final local SGD iterates, enabling valid multiplier bootstrap procedures. Second, motivated by robustness considerations, we introduce two distinct time-uniform Gaussian approximations for the entire trajectory of local SGD. The time-uniform approximations support Gaussian bootstrap-based tests for detecting adversarial attacks. Extensive simulations are provided to support our theoretical results.
title Sharp Gaussian approximations for Decentralized Federated Learning
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2505.08125