Metraipolis › archive › dc_6c044b98c834
Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes — arXiv:2608.09074
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09074
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:02:40.673Z
- SHA-256 of the archived text
c0dfc8221d9a22fdb6c35fd118ab6ae13e953f79d6243457c19e42f95b210d6a- Stable URL of this page
https://metraipolis.com/documento/dc_6c044b98c834
How to cite
Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes — arXiv:2608.09074 — arXiv (en), https://arxiv.org/abs/2608.09074 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c044b98c834 (Metraipolis archive dc_6c044b98c834, sha256 c0dfc8221d9a22fdb6c35fd118ab6ae13e953f79d6243457c19e42f95b210d6a)
BibTeX
@misc{dc6c044b98c834,
title = {Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes — arXiv:2608.09074},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09074},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c044b98c834; sha256 c0dfc8221d9a22fdb6c35fd118ab6ae13e953f79d6243457c19e42f95b210d6a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09074. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop a new approach to Personalized Federated Learning across heterogeneous clients using Nonparametric Empirical Bayes (NPEB). Leveraging the asymptotic normality of local parameter estimates obtained from Empirical Risk Minimization or M-estimation, our method formulates these estimates as noisy observations to estimate an unknown shared prior via Nonparametric Maximum Likelihood. A key challenge in applying NPEB in this setting is that existing approaches assume known fixed variances, which is not true in practice. To address this, we introduce a Variance-Aware Nonparametric Empirical Bayes (VANEB) framework that leverages the parameter-dependent asymptotic variance of local M-estimators. A key technical contribution is a generalized Tweedie's formula for this heteroskedastic setting. We then establish non-asymptotic error rates for density estimation in the average squared Hellinger distance and derive an oracle denoising inequality that provides error bounds for our estimator. While our theoretical guarantees are rooted in the asymptotic regime of M-estimators, we empirically explore heuristic extensions of VANEB to modern federated learning settings involving Deep Neural Networks (DNNs). For DNNs, we propose VANEB-head and VANEB-FT, which personalize the last fully connected layer via an NPEB step using an approximate diagonal variance estimator. We show that our method has strong performance on popular vision datasets MNIST and CIFAR-10, using a convolutional neural network architecture. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in stat.ML). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME). Pagina del lavoro: https://arxiv.org/abs/2608.09074 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:01:32.138Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).