Epistemic Wrapping for Uncertainty Quantification

ICLR 2026 Conference Submission22561 Authors

Keywords: Uncertainty Estimation, Bayesian Neural Networks, Machine Learning Robustness

Abstract: 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 various BNN baselines 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.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 22561