Dropout Inference in Bayesian Neural Networks with Alpha-divergences

TL;DR

This paper introduces a simple method to improve uncertainty estimation in dropout-based Bayesian neural networks by using alpha-divergences, which outperform traditional variational inference in accuracy and uncertainty quantification.

Contribution

The authors propose a re-parametrisation of alpha-divergence objectives enabling easy integration with existing dropout models, enhancing uncertainty estimates without significant model modifications.

Findings

Improved uncertainty estimates over traditional VI in dropout networks.

Enhanced accuracy in predictive performance.

Ability to distinguish adversarial images based on epistemic uncertainty.

Abstract

To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical applications, but VI can severely underestimates model uncertainty. Alpha-divergences are alternative divergences to VI's KL objective, which are able to avoid VI's uncertainty underestimation. But these are hard to use in practice: existing techniques can only use Gaussian approximating distributions, and require existing models to be changed radically, thus are of limited use for practitioners. We propose a re-parametrisation of the alpha-divergence objectives, deriving a simple inference technique which, together with dropout, can be easily implemented with existing models by simply changing the loss of the model. We demonstrate improved uncertainty estimates and accuracy compared to VI in dropout networks. We study our model's epistemic uncertainty far away from the data using adversarial images, showing that these can be distinguished from non-adversarial images by examining our model's uncertainty.