arXiv Statistics ML By Tian Bai, Aaditya Ramdas

A uniform improvement to conformal risk control via a generalization of e-closure

Read the original on arXiv Statistics ML →

The paper extends the e‑closure principle for multiple testing to general state and action spaces and to arbitrarily indexed risk families. It introduces a recertification method that reallocates unused risk budget, enlarging certifying e‑values while preserving validity and yielding less conservative decisions. Applications include improved conformal risk control and enhanced false discovery rate procedures, with empirical gains shown on CIFAR‑100 and simulations.

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 Statistics ML.

arXiv Machine Learning
Sep 30

ReCIRC: Rectified Conformal Risk Control

arXiv:2609.38112v1 Announce Type: cross Abstract: Many applications of black-box predictive models require controlling task-relevant error rates, such as missed lesion pixels in segmentation or misse...

By Bruno Marcondes e Resende, Helton Graziadei, Thiago Rodrigo Ramos, Rafael Izbicki