Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Task. (arXiv:2303.16210v3 [cs.LG] UPDATED)

Deep ensemble is a simple and straightforward approach for approximating
Bayesian inference and has been successfully applied to many classification
tasks. This study aims to comprehensively investigate this approach in the
multi-output regression task to predict the aerodynamic performance of a
missile configuration. By scrutinizing the effect of the number of neural
networks used in the ensemble, an obvious trend toward underconfidence in
estimated uncertainty is observed. In this context, we propose the deep
ensemble framework that applies the post-hoc …

arxiv bayesian bayesian inference classification context ensemble framework inference networks neural networks performance quantification regression study trend uncertainty