Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Machine Learning
2019-06-25 v1 Machine Learning
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.
Cite
@article{arxiv.1906.09686,
title = {Quality of Uncertainty Quantification for Bayesian Neural Network Inference},
author = {Jiayu Yao and Weiwei Pan and Soumya Ghosh and Finale Doshi-Velez},
journal= {arXiv preprint arXiv:1906.09686},
year = {2019}
}
Comments
Accepted to ICML UDL 2019