Conditional validity of heteroskedastic conformal regression

arXiv:2309.08313v2 Announce Type: replace-cross
Abstract: Conformal prediction, and split conformal prediction as a specific implementation, offer a distribution-free approach to estimating prediction intervals with statistical guarantees. Recent work has shown that split conformal prediction can produce state-of-the-art prediction intervals when focusing on marginal coverage, i.e. on a calibration dataset the method produces on average prediction intervals that contain the ground truth with a predefined coverage level. However, such intervals are often not adaptive, which can be problematic for regression problems …

abstract art arxiv coverage cs.lg dataset distribution free implementation prediction regression split state statistical stat.ml type work