New Statistical Framework for Extreme Error Probability in High-Stakes Domains for Reliable Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Michelucci, Umberto, Venturini, Francesca
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916667983921152
author Michelucci, Umberto
Venturini, Francesca
author_facet Michelucci, Umberto
Venturini, Francesca
contents Machine learning is vital in high-stakes domains, yet conventional validation methods rely on averaging metrics like mean squared error (MSE) or mean absolute error (MAE), which fail to quantify extreme errors. Worst-case prediction failures can have substantial consequences, but current frameworks lack statistical foundations for assessing their probability. In this work a new statistical framework, based on Extreme Value Theory (EVT), is presented that provides a rigorous approach to estimating worst-case failures. Applying EVT to synthetic and real-world datasets, this method is shown to enable robust estimation of catastrophic failure probabilities, overcoming the fundamental limitations of standard cross-validation. This work establishes EVT as a fundamental tool for assessing model reliability, ensuring safer AI deployment in new technologies where uncertainty quantification is central to decision-making or scientific analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2503_24262
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle New Statistical Framework for Extreme Error Probability in High-Stakes Domains for Reliable Machine Learning
Michelucci, Umberto
Venturini, Francesca
Machine Learning
Artificial Intelligence
Methodology
Machine learning is vital in high-stakes domains, yet conventional validation methods rely on averaging metrics like mean squared error (MSE) or mean absolute error (MAE), which fail to quantify extreme errors. Worst-case prediction failures can have substantial consequences, but current frameworks lack statistical foundations for assessing their probability. In this work a new statistical framework, based on Extreme Value Theory (EVT), is presented that provides a rigorous approach to estimating worst-case failures. Applying EVT to synthetic and real-world datasets, this method is shown to enable robust estimation of catastrophic failure probabilities, overcoming the fundamental limitations of standard cross-validation. This work establishes EVT as a fundamental tool for assessing model reliability, ensuring safer AI deployment in new technologies where uncertainty quantification is central to decision-making or scientific analysis.
title New Statistical Framework for Extreme Error Probability in High-Stakes Domains for Reliable Machine Learning
topic Machine Learning
Artificial Intelligence
Methodology
url https://arxiv.org/abs/2503.24262