Uncertainty-aware machine learners, such as Bayesian neural networks, output a quantification of uncertainty instead of a point prediction. We provide uncertainty-aware learners with a principled framework to characterize, and identify ways to eliminate, errors that arise from reducible (epistemic) uncertainty. We introduce a principled definition of epistemic error, and provide a decompositional epistemic error bound which operates in the very general setting of imperfect multitask learning under distribution shift. In this setting, the training (source) data may arise from multiple tasks, the test (target) data may differ systematically from the source data tasks, and/or the learner may not arrive at an accurate characterization of the source data. Our bound separately attributes epistemic errors to each of multiple aspects of the learning procedure and environment. As corollaries of the general result, we provide epistemic error bounds specialized to the settings of Bayesian transfer learning and distribution shift within $ε$-neighborhoods.

翻译：不确定性感知的机器学习器（如贝叶斯神经网络）输出不确定性量化结果而非点预测。我们为不确定性感知学习器提供了一个原则性框架，用于表征并识别可消除由可约减（认知性）不确定性产生的错误。我们引入了认知错误的严格定义，并给出了在分布转移下不完美多任务学习这一极其通用场景中的分解式认知错误界限。在此设定下，训练（源）数据可能来自多个任务，测试（目标）数据可能与源数据任务存在系统性差异，且/或学习器可能无法准确刻画源数据。我们的界限将认知错误分别归因于学习过程和环境的多个不同方面。作为一般结果的推论，我们提供了针对贝叶斯迁移学习及$ε$-邻域内分布转移场景的专用认知错误界限。