Tail-Aware Geometry Learning for Conformal Ellipsoids

The paper introduces a tail‑aware geometry learning framework for multivariate conformal prediction using ellipsoids. It decouples tail sensitivity from coverage guarantees by learning a metric matrix through volume minimization under a CVaR constraint, followed by standard conformal calibration. The approach is convex, prioritizes high‑residual samples, and theoretically balances ellipsoidal volume against tail severity, with experiments confirming its effectiveness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.