Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jin, Dian, Bing, Xin, Zhang, Yuqian
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.20532
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908380636905472
author Jin, Dian
Bing, Xin
Zhang, Yuqian
author_facet Jin, Dian
Bing, Xin
Zhang, Yuqian
contents This paper investigates a general robust one-shot aggregation framework for distributed and federated Independent Component Analysis (ICA) problem. We propose a geometric median-based aggregation algorithm that leverages $k$-means clustering to resolve the permutation ambiguity in local client estimations. Our method first performs k-means to partition client-provided estimators into clusters and then aggregates estimators within each cluster using the geometric median. This approach provably remains effective even in highly heterogeneous scenarios where at most half of the clients can observe only a minimal number of samples. The key theoretical contribution lies in the combined analysis of the geometric median's error bound-aided by sample quantiles-and the maximum misclustering rates of the aforementioned solution of $k$-means. The effectiveness of the proposed approach is further supported by simulation studies conducted under various heterogeneous settings.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20532
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One-shot Robust Federated Learning of Independent Component Analysis
Jin, Dian
Bing, Xin
Zhang, Yuqian
Machine Learning
This paper investigates a general robust one-shot aggregation framework for distributed and federated Independent Component Analysis (ICA) problem. We propose a geometric median-based aggregation algorithm that leverages $k$-means clustering to resolve the permutation ambiguity in local client estimations. Our method first performs k-means to partition client-provided estimators into clusters and then aggregates estimators within each cluster using the geometric median. This approach provably remains effective even in highly heterogeneous scenarios where at most half of the clients can observe only a minimal number of samples. The key theoretical contribution lies in the combined analysis of the geometric median's error bound-aided by sample quantiles-and the maximum misclustering rates of the aforementioned solution of $k$-means. The effectiveness of the proposed approach is further supported by simulation studies conducted under various heterogeneous settings.
title One-shot Robust Federated Learning of Independent Component Analysis
topic Machine Learning
url https://arxiv.org/abs/2505.20532