Conformal Prediction Sets Quantify Information Gain: A Theoretical Perspective

Excerpt

arXiv:2610.08785v1 Announce Type: new Abstract: Conformal prediction is a popular tool for uncertainty quantification that outputs prediction sets with finite-sample coverage guarantees. While prediction set size is commonly used as a heuristic measure of uncertainty, the information-theoretic basis for this interpretation remains poorly understood. In this work, we provide such a foundation using a decision-theoretic generalization of entropy tailored to set-valued prediction. In particular, we