Quality of Uncertainty Quantification for Bayesian Neural Network Inference

Abstract

Bayesian Neural Networks (BNNs) place priors over the parameters in a neural network. Inference in BNNs, however, is difficult; all inference methods for BNNs are approximate. In this work, we empirically compare the quality of predictive uncertainty estimates for 10 common inference methods on both regression and classification tasks. Our experiments demonstrate that commonly used metrics (e.g. test log-likelihood) can be misleading. Our experiments also indicate that inference innovations designed to capture structure in the posterior do not necessarily produce high quality posterior approximations.

Accepted to ICML UDL 2019

References in corpus (3)

• Weight Uncertainty in Neural Networks
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Variational Boosting: Iteratively Refining Posterior Approximations

Cited by in corpus (5)

• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Subspace Inference for Bayesian Deep Learning
• Benchmarking the Neural Linear Model for Regression
• Prediction Intervals: Split Normal Mixture from Quality-Driven Deep Ensembles
• Automated Detection of Congenital Heart Disease in Fetal Ultrasound Screening