English

Measuring Uncertainty Calibration

Machine Learning 2026-03-06 v3

Abstract

We make two contributions to the problem of estimating the L1L_1 calibration error of a binary classifier from a finite dataset. First, we provide an upper bound for any classifier where the calibration function has bounded variation. Second, we provide a method of modifying any classifier so that its calibration error can be upper bounded efficiently without significantly impacting classifier performance and without any restrictive assumptions. All our results are non-asymptotic and distribution-free. We conclude by providing advice on how to measure calibration error in practice. Our methods yield practical procedures that can be run on real-world datasets with modest overhead.

Keywords

Cite

@article{arxiv.2512.13872,
  title  = {Measuring Uncertainty Calibration},
  author = {Kamil Ciosek and Nicolò Felicioni and Sina Ghiassian and Juan Elenter Litwin and Francesco Tonolini and David Gustafsson and Eva Garcia-Martin and Carmen Barcena Gonzalez and Raphaëlle Bertrand-Lalo},
  journal= {arXiv preprint arXiv:2512.13872},
  year   = {2026}
}

Comments

ICLR 2026, 28 pages

R2 v1 2026-07-01T08:26:11.425Z