Position: There Is No Free Bayesian Uncertainty Quantification
Not on the map. Why?
Abstract (arXiv)
Due to their intuitive appeal, Bayesian methods of modeling and uncertainty quantification have become popular in modern machine and deep learning. When providing a prior distribution over the parameter space, it is straightforward to obtain a distribution over the parameters that is conventionally interpreted as uncertainty quantification of the model. We challenge the validity of such Bayesian uncertainty quantification by discussing the equivalent optimization-based representation of Bayesian updating, provide an alternative interpretation that is coherent with the optimization-based perspective, propose measures of the quality of the Bayesian inferential stage, and suggest directions for future work.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 27 references that are in the map. First posted on arXiv 4 Jun 2025.
Builds on
11 of 27 references.
References · 11
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 231
- 2019A Primer on PAC-Bayesian Learningcited by 132
- 2017Concentration of tempered posteriors and of their variational approximationscited by 66
- 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 60
- 2019Minimum Description Length Revisitedcited by 37
- 2020PAC Confidence Predictions for Deep Neural Network Classifierscited by 21
- 2023Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetrycited by 21
- 2021Bayesian graph convolutional neural networks via tempered MCMCcited by 9
- 2023Bayesian neural networks via MCMC: a Python-based tutorialcited by 8
- 2017A Tight Excess Risk Bound via a Unified PAC-Bayesian-Rademacher-Shtarkov-MDL Complexitycited by 7
Built on by
Not cited yet.