# Upper Entropy for 2-Monotone Lower Probabilities

Source: [Upper Entropy for 2-Monotone Lower Probabilities](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T05:00:04.194Z

Authors: Tuan-Anh Vu, S\\'ebastien Destercke, Fr\\'ed\\'eric Pichon

Published: 2026-03-23T22:52:25.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Upper entropy computation on Probability Intervals synthetic (test)](<https://www.sota2.com/research/sota/upper-entropy-computation-on-probability-intervals-synthetic-test.md>): Upper entropy computation; Probability Intervals synthetic (test); Runtime (s): 0.265.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.23558>)

[PDF](<https://arxiv.org/pdf/2603.23558.pdf>)
