Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation

Publikation: Artikel i tidsskrift og konference artikel i tidsskriftTidsskriftartikelForskningpeer review

Abstract

Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, 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 comprehensive and extensive 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 other existing methods and provide the most fundamental derivations using a unified notation to aid future research.
OriginalsprogEngelsk
TidsskriftTransactions on Machine Learning Research
ISSN2835-8856
StatusUdgivet - 4 apr. 2023

Emneord

  • Predictive Uncertainty
  • Deep Neural Networks
  • Evidential Deep Learning
  • Uncertainty Estimation
  • Classification and Regression
  • Bayesian Methods
  • Parameterizing Distributions
  • Markov Chain Sampling
  • Monte Carlo Dropout
  • Model Ensembling

Fingeraftryk

Dyk ned i forskningsemnerne om 'Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation'. Sammen danner de et unikt fingeraftryk.

Citationsformater