A Unified Evaluation Framework for Epistemic Predictions

Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Fabio Cuzzolin
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:2017-2025, 2025.

Abstract

Predictions of uncertainty-aware models are diverse, ranging from single point estimates (often averaged over prediction samples) to predictive distributions, to set-valued or credal-set representations. We propose a novel unified evaluation framework for uncertainty-aware classifiers, applicable to a wide range of model classes, which allows users to tailor the trade-off between accuracy and precision of predictions via a suitably designed performance metric. This makes possible the selection of the most suitable model for a particular real-world application as a function of the desired trade-off. Our experiments, concerning Bayesian, ensemble, evidential, deterministic, credal and belief function classifiers on the CIFAR-10, MNIST and CIFAR-100 datasets, show that the metric behaves as desired.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-manchingal25a, title = {A Unified Evaluation Framework for Epistemic Predictions}, author = {Manchingal, Shireen Kudukkil and Mubashar, Muhammad and Wang, Kaizheng and Cuzzolin, Fabio}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {2017--2025}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/manchingal25a/manchingal25a.pdf}, url = {https://proceedings.mlr.press/v258/manchingal25a.html}, abstract = {Predictions of uncertainty-aware models are diverse, ranging from single point estimates (often averaged over prediction samples) to predictive distributions, to set-valued or credal-set representations. We propose a novel unified evaluation framework for uncertainty-aware classifiers, applicable to a wide range of model classes, which allows users to tailor the trade-off between accuracy and precision of predictions via a suitably designed performance metric. This makes possible the selection of the most suitable model for a particular real-world application as a function of the desired trade-off. Our experiments, concerning Bayesian, ensemble, evidential, deterministic, credal and belief function classifiers on the CIFAR-10, MNIST and CIFAR-100 datasets, show that the metric behaves as desired.} }
Endnote
%0 Conference Paper %T A Unified Evaluation Framework for Epistemic Predictions %A Shireen Kudukkil Manchingal %A Muhammad Mubashar %A Kaizheng Wang %A Fabio Cuzzolin %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-manchingal25a %I PMLR %P 2017--2025 %U https://proceedings.mlr.press/v258/manchingal25a.html %V 258 %X Predictions of uncertainty-aware models are diverse, ranging from single point estimates (often averaged over prediction samples) to predictive distributions, to set-valued or credal-set representations. We propose a novel unified evaluation framework for uncertainty-aware classifiers, applicable to a wide range of model classes, which allows users to tailor the trade-off between accuracy and precision of predictions via a suitably designed performance metric. This makes possible the selection of the most suitable model for a particular real-world application as a function of the desired trade-off. Our experiments, concerning Bayesian, ensemble, evidential, deterministic, credal and belief function classifiers on the CIFAR-10, MNIST and CIFAR-100 datasets, show that the metric behaves as desired.
APA
Manchingal, S.K., Mubashar, M., Wang, K. & Cuzzolin, F.. (2025). A Unified Evaluation Framework for Epistemic Predictions. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:2017-2025 Available from https://proceedings.mlr.press/v258/manchingal25a.html.

Related Material