Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation
Not on the map. Why?
Abstract (arXiv)
Reliable uncertainty quantification is essential for the use of machine learning in physics, where scientific discoveries depend on validated probabilistic statements. We provide a structured overview of uncertainty quantification in ML for physics, introducing a unified taxonomy of uncertainty and clarifying the interpretation of predictive and inference uncertainties across frequentist and Bayesian frameworks. We discuss principled validation tools, including coverage, calibration, bias tests, and proper scoring rules, and illustrate them with simple regression and classification examples.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 46 of its 133 references that are in the map. First posted on arXiv 11 May 2026.
Builds on
46 of 133 references.
References · 46
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2016Variational Inference: A Review for Statisticianscited by 1,472
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
- 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
- 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
- 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
- 2019Deep Evidential Regressioncited by 355
34 more
- 2014Stochastic Gradient Hamiltonian Monte Carlocited by 343
- 2021User-friendly introduction to PAC-Bayes boundscited by 239
- 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 209
- 2021Equinox: neural networks in JAX via callable PyTrees and filtered transformationscited by 148
- 2019Functional Variational Bayesian Neural Networkscited by 127
- 2021Repulsive Deep Ensembles are Bayesiancited by 104
- 2016PAC-Bayesian Theory Meets Bayesian Inferencecited by 88
- 2019Calibration tests in multi-class classification: A unifying frameworkcited by 79
- 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
- 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62
- 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 42
- 2023Tractable Function-Space Variational Inference in Bayesian Neural Networkscited by 41
- 2022The Unreasonable Effectiveness of Deep Evidential Regressioncited by 40
- 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 35
- 2023Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' Viewcited by 28
- 2024BlackJAX: Composable Bayesian inference in JAXcited by 26
- 2021Multivariate Deep Evidential Regressioncited by 23
- 2022Calibration tests beyond classificationcited by 20
- 2024The Landscape of Unfolding with Machine Learningcited by 20
- 2021Understanding Event-Generation Networks via Uncertaintiescited by 17
- 2021A Cautionary Tale of Decorrelating Theory Uncertaintiescited by 11
- 2024A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learningcited by 10
- 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 9
- 2022Interpretable Uncertainty Quantification in AI for HEPcited by 8
- 2024Calibrating Bayesian Generative Machine Learning for Bayesiamplificationcited by 5
- 2023ELUQuant: Event-Level Uncertainty Quantification in Deep Inelastic Scatteringcited by 3
- 2025Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networkscited by 3
- 2017Bayesian Methods in Cosmologycited by 2
- 2025Another Fit Bites the Dust: Conformal Prediction as a Calibration Standard for Machine Learning in High-Energy Physicscited by 2
- 2026Improving Generalization and Uncertainty Quantification of Photometric Redshift Modelscited by 2
- 2026FAIR Universe Weak Lensing ML Uncertainty Challenge: Handling Uncertainties and Distribution Shifts for Precision Cosmologycited by 2
- 2025Bayesian Computation in Deep Learningcited by 1
- 2026Uncertainty-Aware Solar Flare Regressioncited by 1
- 2026A plug-and-play approach with fast uncertainty quantification for weak lensing mass mappingcited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.