Stein Variational Newton Neural Network Ensembles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Flöge, Klemens, Moeed, Mohammed Abdul, Fortuin, Vincent
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915003971403776
author Flöge, Klemens
Moeed, Mohammed Abdul
Fortuin, Vincent
author_facet Flöge, Klemens
Moeed, Mohammed Abdul
Fortuin, Vincent
contents Deep neural network ensembles are powerful tools for uncertainty quantification, which have recently been re-interpreted from a Bayesian perspective. However, current methods inadequately leverage second-order information of the loss landscape, despite the recent availability of efficient Hessian approximations. We propose a novel approximate Bayesian inference method that modifies deep ensembles to incorporate Stein Variational Newton updates. Our approach uniquely integrates scalable modern Hessian approximations, achieving faster convergence and more accurate posterior distribution approximations. We validate the effectiveness of our method on diverse regression and classification tasks, demonstrating superior performance with a significantly reduced number of training epochs compared to existing ensemble-based methods, while enhancing uncertainty quantification and robustness against overfitting.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01887
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stein Variational Newton Neural Network Ensembles
Flöge, Klemens
Moeed, Mohammed Abdul
Fortuin, Vincent
Machine Learning
Deep neural network ensembles are powerful tools for uncertainty quantification, which have recently been re-interpreted from a Bayesian perspective. However, current methods inadequately leverage second-order information of the loss landscape, despite the recent availability of efficient Hessian approximations. We propose a novel approximate Bayesian inference method that modifies deep ensembles to incorporate Stein Variational Newton updates. Our approach uniquely integrates scalable modern Hessian approximations, achieving faster convergence and more accurate posterior distribution approximations. We validate the effectiveness of our method on diverse regression and classification tasks, demonstrating superior performance with a significantly reduced number of training epochs compared to existing ensemble-based methods, while enhancing uncertainty quantification and robustness against overfitting.
title Stein Variational Newton Neural Network Ensembles
topic Machine Learning
url https://arxiv.org/abs/2411.01887