Empirical-Bayes spectral partial pooling across related tasks

Abstract

Spectral methods are central to high-dimensional statistics and machine learning, underlying procedures for covariance estimation, matrix denoising, representation learning, clustering, and latent variable modeling. In this work, we focus primarily on spectral estimators for high-dimensional factor models, where leading singular vectors of the data matrix are used to estimate latent structure and covariance parameters. In many modern applications, however, data are collected across related but heterogeneous tasks, studies, domains, or populations. Applying such estimators separately to each task can lead to unstable estimates when sample sizes are limited relative to dimension, while completely pooling the data can obscure meaningful task-specific structure. We introduce Hierarchical Spectral Shrinkage (\texttt{HSS}), a scalable empirical-Bayes framework for partially pooling task-specific spectral estimators. The method regularizes the leading spectral directions of each task toward a data-adaptivelylearned common basis, while allowing the amount of shrinkage to vary across tasks and spectral components. The proposed estimator arises as the posterior mean in a surrogate Bayesian regression formulation of the empirical singular vectors. For factor models, \texttt{HSS} yields partially pooled estimators of the group-specific loading spaces and covariance matrices and can be combined with different spectral estimators by replacing their empirical singular vectors with hierarchically regularized counterparts. More broadly, the same construction provides a mechanism for extending spectral estimators to collections of related but heterogeneous datasets. We demonstrate substantial improvements in estimation accuracy and out-of-sample performance over separate, fully pooled, and shared-subspace approaches in synthetic experiments and multi-study gene-expression data.

The Geometry of Informativeness: A Bregman-Centroid Diagnostic for Partial Pooling in Multisite Trials
JoonHo Lee
arXiv17 Oct 2026PreprintarXiv licenceFull textStatisticsarXiv
Using Temporal Replication and Partial Pooling to Improve Practical Identifiability in Presence-Only Poisson Point Process Models
Camille Mottier, Iris Lang, Justine Nicolas +1
arXiv21 Oct 2026PreprintCC BY 4.0Full textStatisticsarXiv
Pooling Sequential Evidence Across Hypotheses: Rate-Optimal Multiple Testing at a Fixed Horizon
Prasanjit Dubey, Xiaoming Huo
arXiv23 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
The INSIDE assumption under all positive coding: interpretation and partial empirical assessment
Fernando Pires Hartwig, George Davey Smith, Frank Dudbridge +1
arXiv29 Sep 2026PreprintCC BY 4.0Full textStatisticsarXiv
A comparison of artificial neural networks and partial least squares modelling for the rapid detection of the microbial spoilage of beef fillets based on Fourier transform infrared spectral fingerprints
Efstathios Panagou, Fady Mohareb, Anthoula Argyri +2
Food Microbiology9 Oct 2026Peer-reviewedLicence not statedFull text76 citedGeneral biology StatisticsHAL

Cite

BibTeX RIS

BibTeX

@misc{mauri2026empiricalbayes,
  title = {{Empirical-Bayes spectral partial pooling across related tasks}},
  author = {Lorenzo Mauri},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.07284},
  eprint = {2610.07284},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.07284},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Empirical-Bayes spectral partial pooling across related tasks
AU  - Lorenzo Mauri
PY  - 2026
DA  - 2026/10/05
PB  - arXiv
DO  - 10.48550/arxiv.2610.07284
UR  - https://arxiv.org/abs/2610.07284
AB  - Spectral methods are central to high-dimensional statistics and machine learning, underlying procedures for covariance estimation, matrix denoising, representation learning, clustering, and latent variable modeling. In this work, we focus primarily on spectral estimators for high-dimensional factor models, where leading singular vectors of the data matrix are used to estimate latent structure and covariance parameters. In many modern applications, however, data are collected across related but heterogeneous tasks, studies, domains, or populations. Applying such estimators separately to each task can lead to unstable estimates when sample sizes are limited relative to dimension, while completely pooling the data can obscure meaningful task-specific structure. We introduce Hierarchical Spectral Shrinkage (\texttt{HSS}), a scalable empirical-Bayes framework for partially pooling task-specific spectral estimators. The method regularizes the leading spectral directions of each task toward a data-adaptivelylearned common basis, while allowing the amount of shrinkage to vary across tasks and spectral components. The proposed estimator arises as the posterior mean in a surrogate Bayesian regression formulation of the empirical singular vectors. For factor models, \texttt{HSS} yields partially pooled estimators of the group-specific loading spaces and covariance matrices and can be combined with different spectral estimators by replacing their empirical singular vectors with hierarchically regularized counterparts. More broadly, the same construction provides a mechanism for extending spectral estimators to collections of related but heterogeneous datasets. We demonstrate substantial improvements in estimation accuracy and out-of-sample performance over separate, fully pooled, and shared-subspace approaches in synthetic experiments and multi-study gene-expression data.
ER  -

Abstract

Related

Cite