Upper Entropy for 2-Monotone Lower Probabilities
This work addresses uncertainty quantification in credal approaches, offering more efficient algorithms for a specific mathematical framework.
The paper tackles the computational complexity of calculating upper entropy for 2-monotone lower probabilities, showing it has a strongly polynomial solution and proposing algorithmic improvements over prior methods.
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.