Epistemic Wrapping for Uncertainty Quantification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913997193740288 |
|---|---|
| author | Sultana, Maryam Yorke-Smith, Neil Wang, Kaizheng Manchingal, Shireen Kudukkil Mubashar, Muhammad Cuzzolin, Fabio |
| author_facet | Sultana, Maryam Yorke-Smith, Neil Wang, Kaizheng Manchingal, Shireen Kudukkil Mubashar, Muhammad Cuzzolin, Fabio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Epistemic Wrapping for Uncertainty Quantification Sultana, Maryam Yorke-Smith, Neil Wang, Kaizheng Manchingal, Shireen Kudukkil Mubashar, Muhammad Cuzzolin, Fabio Machine Learning 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. |
| title | Epistemic Wrapping for Uncertainty Quantification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.02277 |