SyncAI.news, a Varaisys broadcasting
Anytime-Valid Conformal Risk Control
BH

Bror Hultberg, Dave Zachariah, Ant\^onio H. Ribeiro

· 1 min read

ResearcharXiv cs.LG

Anytime-Valid Conformal Risk Control

arXiv:2602.04364v2 Announce Type: replace-cross Abstract: Prediction sets provide a means of quantifying the uncertainty in predictive tasks. Using held out calibration data, conformal prediction and risk control can produce prediction sets that exhibit statistically valid error control in a computationally efficient manner. However, in the standard formulations, the error is only controlled on average over many possible calibration datasets of fixed size. In this paper, we extend the control to remain valid with high probability over a cumulatively growing calibration dataset at any time point. We derive such guarantees using quantile-based arguments and illustrate the applicability of the proposed framework to settings involving distribution shift. We further show that our guarantees are asymptotically tight, in the sense that the risks converge to the target level from below, and that the rate of our correction cannot be improved. Finally, we demonstrate the practical performance of our methods through both simulations and real-world numerical examples.

Original source

This story was published by arXiv cs.LG and written by Bror Hultberg, Dave Zachariah, Ant\^onio H. Ribeiro. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News