Upper entropy for 2-monotone lower probabilities

Tuan-Anh Vu, Sebastien Destercke, Frédéric Pichon
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:7023-7035, 2026.

Abstract

Uncertainty quantification is a key aspect in many tasks such as model selection/regularization, or quantifying prediction uncertainties to perform active learning or {OOD} detection. Within credal approaches that consider modeling uncertainty as probability sets, upper entropy plays a central role as an uncertainty measure. This paper is devoted to the computational aspect of upper entropies, providing an exhaustive algorithmic and complexity analysis of the problem. In particular, we show that the problem has a strongly polynomial solution, and propose many significant improvements over past algorithms proposed for 2-monotone lower probabilities and their specific cases.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-vu26a, title = {Upper entropy for 2-monotone lower probabilities}, author = {Vu, Tuan-Anh and Destercke, Sebastien and Pichon, Fr\'{e}d\'{e}ric}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {7023--7035}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/vu26a/vu26a.pdf}, url = {https://proceedings.mlr.press/v337/vu26a.html}, abstract = {Uncertainty quantification is a key aspect in many tasks such as model selection/regularization, or quantifying prediction uncertainties to perform active learning or {OOD} detection. Within credal approaches that consider modeling uncertainty as probability sets, upper entropy plays a central role as an uncertainty measure. This paper is devoted to the computational aspect of upper entropies, providing an exhaustive algorithmic and complexity analysis of the problem. In particular, we show that the problem has a strongly polynomial solution, and propose many significant improvements over past algorithms proposed for 2-monotone lower probabilities and their specific cases.} }
Endnote
%0 Conference Paper %T Upper entropy for 2-monotone lower probabilities %A Tuan-Anh Vu %A Sebastien Destercke %A Frédéric Pichon %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-vu26a %I PMLR %P 7023--7035 %U https://proceedings.mlr.press/v337/vu26a.html %V 337 %X Uncertainty quantification is a key aspect in many tasks such as model selection/regularization, or quantifying prediction uncertainties to perform active learning or {OOD} detection. Within credal approaches that consider modeling uncertainty as probability sets, upper entropy plays a central role as an uncertainty measure. This paper is devoted to the computational aspect of upper entropies, providing an exhaustive algorithmic and complexity analysis of the problem. In particular, we show that the problem has a strongly polynomial solution, and propose many significant improvements over past algorithms proposed for 2-monotone lower probabilities and their specific cases.
APA
Vu, T., Destercke, S. & Pichon, F.. (2026). Upper entropy for 2-monotone lower probabilities. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:7023-7035 Available from https://proceedings.mlr.press/v337/vu26a.html.

Related Material