Epistemic Wrapping for Uncertainty Quantification
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 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.
Cite
@article{arxiv.2505.02277,
title = {Epistemic Wrapping for Uncertainty Quantification},
author = {Maryam Sultana and Neil Yorke-Smith and Kaizheng Wang and Shireen Kudukkil Manchingal and Muhammad Mubashar and Fabio Cuzzolin},
journal= {arXiv preprint arXiv:2505.02277},
year = {2025}
}