Accurate uncertainty quantification is critical for reliable predictive modeling. Existing methods typically address either aleatoric uncertainty due to measurement noise or epistemic uncertainty resulting from limited data, but not both in a balanced manner. We propose CLEAR, a calibration method with two distinct parameters, $γ_1$ and $γ_2$, to combine the two uncertainty components and improve the conditional coverage of predictive intervals for regression tasks. CLEAR is compatible with any pair of aleatoric and epistemic estimators; we show how it can be used with (i) quantile regression for aleatoric uncertainty and (ii) ensembles drawn from the Predictability-Computability-Stability (PCS) framework for epistemic uncertainty. Across 17 diverse real-world datasets, CLEAR achieves an average improvement of 28.3\% and 17.5\% in the interval width compared to the two individually calibrated baselines while maintaining nominal coverage. Similar improvements are observed when applying CLEAR to Deep Ensembles (epistemic) and Simultaneous Quantile Regression (aleatoric). The benefits are especially evident in scenarios dominated by high aleatoric or epistemic uncertainty. Project page: https://unco3892.github.io/clear/

翻译：精确的不确定性量化对于可靠的预测建模至关重要。现有方法通常单独处理由测量噪声引起的偶然不确定性或由数据有限导致的认知不确定性，但未能以平衡的方式同时处理两者。我们提出CLEAR，这是一种具有两个独立参数$γ_1$和$γ_2$的校准方法，用于结合两种不确定性成分，并改进回归任务中预测区间的条件覆盖度。CLEAR兼容任意一对偶然与认知不确定性估计器；我们展示了如何将其与（i）用于偶然不确定性的分位数回归以及（ii）从可预测性-可计算性-稳定性（PCS）框架中抽取的集成方法（用于认知不确定性）结合使用。在17个不同的真实世界数据集上，与两个单独校准的基线方法相比，CLEAR在保持名义覆盖度的同时，将区间宽度平均改善了28.3%和17.5%。将CLEAR应用于深度集成（认知）与同步分位数回归（偶然）时也观察到类似的改进。在由高偶然或高认知不确定性主导的场景中，其优势尤为明显。项目页面：https://unco3892.github.io/clear/