Stein Variational Newton Neural Network Ensembles

Klemens Flöge, Muhammad Abdul Moeed, Vincent Fortuin

Keywords: Uncertainty Quantification, Bayesian Neural Networks, Approximate Bayesian Inference, Bayesian Deep Learning, Hessian Computation

TL;DR: We propose a novel method that integrates Stein Variational Newton updates with deep neural network ensembles using scalable Hessian approximations, achieving faster convergence and improved uncertainty quantification.

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.

Submission Number: 38