[2603.23558] Upper Entropy for 2-Monotone Lower Probabilities

Computer Science > Machine Learning arXiv:2603.23558 (cs) [Submitted on 23 Mar 2026] Title:Upper Entropy for 2-Monotone Lower Probabilities Authors:Tuan-Anh Vu, Sébastien Destercke, Frédéric Pichon View a PDF of the paper titled Upper Entropy for 2-Monotone Lower Probabilities, by Tuan-Anh Vu and 2 other authors View PDF HTML (experimental) 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. Comments: Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.23558 [cs.LG]   (or arXiv:2603.23558v1 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2603.23558 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Sebastien Destercke [view email] [v1] Mon, 23 Mar 2026 22:52:25 UTC (44 KB) Full-text links: Access Paper: View a PDF of the paper titled Upper Entropy for 2-Mo...