Deep Ensembles from a Bayesian Perspective
This work provides a theoretical foundation for deep ensembles, potentially improving uncertainty estimation in machine learning applications.
The paper tackles the problem of uncertainty quantification in deep learning by showing that deep ensembles can be viewed as an approximate Bayesian method, leading to an improved approximation that enlarges epistemic uncertainty and results in more reliable uncertainties.
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. Numerical examples suggest that the improved approximation can lead to more reliable uncertainties. Analytical derivations ensure easy calculation of results.