Saved in:
Bibliographic Details
Main Authors: Fermanian, Jean-Baptiste, Bars, Batiste Le, Bellet, Aurélien
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.02233
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915829996584960
author Fermanian, Jean-Baptiste
Bars, Batiste Le
Bellet, Aurélien
author_facet Fermanian, Jean-Baptiste
Bars, Batiste Le
Bellet, Aurélien
contents Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents' empirical risks, with the weights learned from data rather than specified a priori. The novelty of our method lies in formulating the estimation of these collaborative weights as a kernel mean embedding estimation problem with multiple data sources, leveraging tools from multi-task averaging to capture statistical relationships between agents. This perspective yields a fully adaptive procedure that requires no prior knowledge of data heterogeneity and can automatically transition between global and local learning regimes. By recasting the objective as a high-dimensional mean estimation problem, we derive finite-sample guarantees on local excess risks for a broad class of distributions, explicitly quantifying the statistical gains of collaboration. To address communication constraints inherent to federated settings, we also propose a practical implementation based on random Fourier features, which allows one to trade communication cost for statistical efficiency. Numerical experiments validate our theoretical results.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02233
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
Fermanian, Jean-Baptiste
Bars, Batiste Le
Bellet, Aurélien
Machine Learning
Artificial Intelligence
Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents' empirical risks, with the weights learned from data rather than specified a priori. The novelty of our method lies in formulating the estimation of these collaborative weights as a kernel mean embedding estimation problem with multiple data sources, leveraging tools from multi-task averaging to capture statistical relationships between agents. This perspective yields a fully adaptive procedure that requires no prior knowledge of data heterogeneity and can automatically transition between global and local learning regimes. By recasting the objective as a high-dimensional mean estimation problem, we derive finite-sample guarantees on local excess risks for a broad class of distributions, explicitly quantifying the statistical gains of collaboration. To address communication constraints inherent to federated settings, we also propose a practical implementation based on random Fourier features, which allows one to trade communication cost for statistical efficiency. Numerical experiments validate our theoretical results.
title Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.02233