Reliable Uncertainties for Bayesian Neural Networks using Alpha-divergences

, ,

ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning (2020) .


Abstract

Bayesian Neural Networks (BNNs) often result uncalibrated after training, usually tending towards overconfidence. Devising effective calibration methods with low impact in terms of computational complexity is thus of central interest. In this paper we present calibration methods for BNNs based on the alpha divergences from Information Geometry. We compare the use of alpha divergence in training and in calibration, and we show how the use in calibration provides better-calibrated uncertainty estimates for specific choices of alpha and is more efficient especially for complex network architectures. We empirically demonstrate the advantages of alpha calibration in regression problems involving parameter estimation and inferred correlations between output uncertainties.



Add your rating and review

If all scientific publications that you have read were ranked according to their scientific quality and importance from 0% (worst) to 100% (best), where would you place this publication? Please rate by selecting a range.


0% - 100%

This publication ranks between % and % of publications that I have read in terms of scientific quality and importance.


Keep my rating and review anonymous
Show publicly that I gave the rating and I wrote the review



Notice: Undefined index: publicationsCaching in /www/html/epistemio/application/controllers/PublicationController.php on line 2240