arXiv:2607.14817 · v2

Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning

首次提交 2026-07-16 18:35

版本更新 2026-11-09 20:10

雷达观测 2026-11-10 15:22

摘要

Current evaluation of epistemic uncertainty relies on tasks such as out-of-distribution detection, active learning and selective prediction. However, common epistemic uncertainty scores, such as mutual information or the variance of the predictions, estimate the regret, the excess error of a predictor over the Bayes-optimal predictor. Building on the epistemic reject-option framework, we evaluate epistemic uncertainty using its ability to identify regret, and compare this evaluation with the other tasks. Benchmarking standard methods on datasets with repeated human labels reveals that the tasks rank the methods differently, including pairwise rank inversions between methods that are top-ranked on one criterion and bottom-ranked on another. The disagreement is present already at the optimum, where each task calls for a different score. Formulating selective prediction as a constrained optimization over coverage, expected risk, and regret, we prove that the optimal score is a convex combination of the ground-truth aleatoric and epistemic uncertainties, so that selective prediction and the regret task are the two endpoints of one family of tasks. Out-of-distribution detection, active learning and the regret task thus disagree, theoretically as well as empirically, on which method is a good estimator of epistemic uncertainty, while selective prediction departs from the regret task where the true risk and the regret order the inputs differently. Researchers must therefore state the downstream decision that an epistemic uncertainty estimate is meant to support, instead of relying on a general notion of model ignorance.

作者备注：Neurips 2026