Saved in:
Bibliographic Details
Main Authors: Zamyatin, Anton, Indri, Patrick, Malhotra, Sagar, Gärtner, Thomas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16936
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914275712303104
author Zamyatin, Anton
Indri, Patrick
Malhotra, Sagar
Gärtner, Thomas
author_facet Zamyatin, Anton
Indri, Patrick
Malhotra, Sagar
Gärtner, Thomas
contents In resource-constrained and low-latency settings, uncertainty estimates must be efficiently obtained. Deep Ensembles provide robust epistemic uncertainty (EU) but require training multiple full-size models. BatchEnsemble aims to deliver ensemble-like EU at far lower parameter and memory cost by applying learned rank-1 perturbations to a shared base network. We show that BatchEnsemble not only underperforms Deep Ensembles but closely tracks a single model baseline in terms of accuracy, calibration and out-of-distribution (OOD) detection on CIFAR10/10C/SVHN. A controlled study on MNIST finds members are near-identical in function and parameter space, indicating limited capacity to realize distinct predictive modes. Thus, BatchEnsemble behaves more like a single model than a true ensemble.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16936
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles
Zamyatin, Anton
Indri, Patrick
Malhotra, Sagar
Gärtner, Thomas
Machine Learning
In resource-constrained and low-latency settings, uncertainty estimates must be efficiently obtained. Deep Ensembles provide robust epistemic uncertainty (EU) but require training multiple full-size models. BatchEnsemble aims to deliver ensemble-like EU at far lower parameter and memory cost by applying learned rank-1 perturbations to a shared base network. We show that BatchEnsemble not only underperforms Deep Ensembles but closely tracks a single model baseline in terms of accuracy, calibration and out-of-distribution (OOD) detection on CIFAR10/10C/SVHN. A controlled study on MNIST finds members are near-identical in function and parameter space, indicating limited capacity to realize distinct predictive modes. Thus, BatchEnsemble behaves more like a single model than a true ensemble.
title Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles
topic Machine Learning
url https://arxiv.org/abs/2601.16936