Conformal Prediction Regions Are Imprecise Highest Density Regions
Abstract
Recently, Cella and Martin proved how, under an assumption called consonance, a credal set (i.e. a closed and convex set of probabilities) can be derived from the conformal transducer associated with transductive conformal prediction. We show that the Imprecise Highest Density Region (IHDR) associated with such a credal set corresponds to the classical Conformal Prediction Region. In proving this result, we establish a new relationship between Conformal Prediction and Imprecise Probability (IP) theories, via the IP concept of a cloud. A byproduct of our presentation is the discovery that consonant plausibility functions are monoid homomorphisms, a new algebraic property of an IP tool.
Cite
Text
Caprio et al. "Conformal Prediction Regions Are Imprecise Highest Density Regions." Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications, 2025.Markdown
[Caprio et al. "Conformal Prediction Regions Are Imprecise Highest Density Regions." Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications, 2025.](https://mlanthology.org/isipta/2025/caprio2025isipta-conformal/)BibTeX
@inproceedings{caprio2025isipta-conformal,
title = {{Conformal Prediction Regions Are Imprecise Highest Density Regions}},
author = {Caprio, Michele and Sale, Yusuf and Hüllermeier, Eyke},
booktitle = {Proceedings of the Fourteenth International Symposium on Imprecise Probabilities: Theories and Applications},
year = {2025},
pages = {47-59},
volume = {290},
url = {https://mlanthology.org/isipta/2025/caprio2025isipta-conformal/}
}