Deep Ensembles from a Bayesian Perspective [article]

Lara Hoffmann, Clemens Elster
2021 arXiv   pre-print
Deep ensembles can be considered as the current state-of-the-art for uncertainty quantification in deep learning. While the approach was originally proposed as a non-Bayesian technique, arguments supporting its Bayesian footing have been put forward as well. We show that deep ensembles can be viewed as an approximate Bayesian method by specifying the corresponding assumptions. Our findings lead to an improved approximation which results in an enlarged epistemic part of the uncertainty.
more » ... examples suggest that the improved approximation can lead to more reliable uncertainties. Analytical derivations ensure easy calculation of results.
arXiv:2105.13283v2 fatcat:stxol5heqrbypc7suuv5uqer5q