An Information Theoretic Perspective on Conformal Prediction

arXiv:2405.02140v1 Announce Type: new
Abstract: Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a general notion of uncertainty, with larger sets associated with higher degrees of uncertainty. In this work, we leverage information theory to connect conformal prediction to other notions of uncertainty. More precisely, we prove three different ways to upper bound the intrinsic uncertainty, as …

abstract arxiv cs.it cs.lg distribution framework free general information math.it notion perspective prediction probability set stat.ml true type uncertainty work