Beyond the Norms: Detecting Prediction Errors in Regression Models

TL;DR

This paper introduces a novel probabilistic approach to detect unreliable predictions in regression models by estimating discrepancy density and measuring statistical dissimilarity, improving error detection across various tasks.

Contribution

It formally defines unreliability in regression, proposes a new metric for statistical dissimilarity, and develops a data-driven uncertainty score that outperforms existing methods.

Findings

Empirical improvements in error detection accuracy

Consistent outperforming of baseline approaches

Enhanced uncertainty quantification in regression

Abstract

This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g., aleatoric uncertainty) or modeling errors (e.g., model uncertainty). First, we formally introduce the notion of unreliability in regression, i.e., when the output of the regressor exceeds a specified discrepancy (or error). Then, using powerful tools for probabilistic modeling, we estimate the discrepancy density, and we measure its statistical diversity using our proposed metric for statistical dissimilarity. In turn, this allows us to derive a data-driven score that expresses the uncertainty of the regression outcome. We show empirical improvements in error detection for multiple regression tasks, consistently outperforming popular baseline approaches, and contributing to the broader field of uncertainty quantification and safe machine learning systems. Our code is available at https://zenodo.org/records/11281964.