Stein Variational Newton Neural Network Ensembles

TL;DR

This paper introduces a novel Bayesian inference method that enhances deep neural network ensembles with Stein Variational Newton updates, leveraging Hessian approximations for faster convergence and improved uncertainty quantification.

Contribution

It presents a new approach combining Stein Variational Newton updates with scalable Hessian approximations to improve Bayesian neural network ensembles.

Findings

Faster convergence compared to traditional ensembles.

More accurate posterior distribution approximations.

Enhanced uncertainty quantification and robustness.

Abstract

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.