arXiv stat.ML
· Papers
Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
arXiv:2608.06206v1 Announce Type: new Abstract: Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscalibration, while exact distribution-free conditional coverage is finite-sample unattainable. R