Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals
Abstract
Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI. In regression tasks, uncertainty is typically quantified using prediction intervals calibrated to a specific operating point, making evaluation and comparison across different studies difficult. Our work leverages: (1) the concept of operating characteristics curves and (2) the notion of a gain over a simple reference, to derive a novel operating point agnostic assessment methodology for prediction intervals. The paper describes the corresponding algorithm, provides a theoretical analysis, and demonstrates its utility in multiple scenarios. We argue that the proposed method addresses the current need for comprehensive assessment of prediction intervals and thus represents a valuable addition to the uncertainty quantification toolbox.
Keywords
Cite
@article{arxiv.2106.00858,
title = {Uncertainty Characteristics Curves: A Systematic Assessment of Prediction Intervals},
author = {Jiri Navratil and Benjamin Elder and Matthew Arnold and Soumya Ghosh and Prasanna Sattigeri},
journal= {arXiv preprint arXiv:2106.00858},
year = {2021}
}
Comments
10 pages main paper, 9 pages appendix