Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
Abstract: Popular approaches for quantifying predictive uncertainty in deep neural networks often involve multiple sets of weights or models, for instance, via ensembling or Monte Carlo dropout. These techniques usually incur overhead by having to train multiple model instances or do not produce very diverse predictions. This survey aims to familiarize the reader with an alternative class of models based on the concept of Evidential Deep Learning: For unfamiliar data, they admit “what they don’t know” and fall back onto a prior belief. Furthermore, they allow uncertainty estimation in a single model and forward pass by parameterizing distributions over distributions. This survey recapitulates existing works, focusing on the implementation in a classification setting, before surveying the application of the same paradigm to regression. We also reflect on the strengths and weaknesses compared to each other as well as to more established methods and provide the most central theoretical results using a unified notation in order to aid future research.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Jasper_Snoek1
Submission Number: 248
Loading