mlsanityData to 14 Oct 2026

Epistemic Wrapping for Uncertainty Quantification

arXiv 2505.02277 ↗First posted 4 May 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Uncertainty estimation is pivotal in machine learning, especially for classification tasks, as it improves the robustness and reliability of models. We introduce a novel `Epistemic Wrapping' methodology aimed at improving uncertainty estimation in classification. Our approach uses Bayesian Neural Networks (BNNs) as a baseline and transforms their outputs into belief function posteriors, effectively capturing epistemic uncertainty and offering an efficient and general methodology for uncertainty quantification. Comprehensive experiments employing a Bayesian Neural Network (BNN) baseline and an Interval Neural Network for inference on the MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 datasets demonstrate that our Epistemic Wrapper significantly enhances generalisation and uncertainty quantification.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 27 of its 52 references that are in the map. First posted on arXiv 4 May 2025.

Builds on

27 of 52 references.

References · 27

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2016Variational Inference: A Review for Statisticianscited by 1,472
  4. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  5. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  6. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  7. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  8. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
  9. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  10. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  11. 2019Ensemble Distribution Distillationcited by 158
  12. 2019Practical Deep Learning with Bayesian Principlescited by 158
15 more
  1. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  2. 2019Large Scale Structure of Neural Network Loss Landscapescited by 68
  3. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 54
  4. 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
  5. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 35
  6. 2024Credal Learning Theorycited by 31
  7. 2024CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Taskscited by 26
  8. 2023Random-Set Neural Networks (RS-NN)cited by 19
  9. 2022Epistemic Deep Learningcited by 15
  10. 2024Energy-based Epistemic Uncertainty for Graph Neural Networkscited by 14
  11. 2025A Unified Evaluation Framework for Epistemic Predictionscited by 10
  12. 2021Uncertainty measures: The big picturecited by 8
  13. 2024Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networkscited by 8
  14. 2024Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networkscited by 3
  15. 2013The Transferable Belief Model and Other Interpretations of Dempster-Shafer's Modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  2. 2026Epistemic Generative Adversarial Networkscited by 4
  3. 2026Random-Set Graph Neural Networkscited by 3
  4. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  5. 2026A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classificationcited by 1