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.
翻译:长期以来,对模型不确定性的准确量化被公认为信任的AI的基本要求。在回归任务中,不确定性通常是通过根据具体操作点校准的预测间隔量量化的,使得不同研究很难进行评估和比较。我们的工作杠杆:(1) 操作特征曲线的概念和(2) 利用简单参考获得收益的概念,为预测间隔得出一种新的操作点不可知性评估方法。本文描述了相应的算法,提供了理论分析,并展示了它在多种情况下的效用。我们争辩说,拟议方法解决了目前全面评估预测间隔的需要,因此是对不确定性量化工具箱的宝贵补充。