提出可量化认知误差的框架，揭示多任务学习在分布漂移下的不确定性来源。
Epistemic Errors of Imperfect Multitask Learners When Distributions Shift
- 定义认知误差并分解为多环节贡献，适用于不完美多任务学习场景。
- 在分布偏移下，理论证明误差可被系统性归因并减少。
- 适合关注鲁棒性与可信机器学习的研究者或工程师。
具备不确定性感知能力的机器学习模型（如贝叶斯神经网络）输出不确定性度量而非单一预测。本文为这类模型提供一个原理性框架，用于刻画并识别由可减少的认知不确定性（epistemic uncertainty）引发的误差。我们提出了认知误差的严格定义，并推导出一个通用的分解式认知误差界，适用于存在分布偏移的不完美多任务学习场景。在此设定中，训练数据可能来自多个任务，测试数据可能与源任务系统性不同，或学习器未能准确表征源数据。该误差界能分别归因于学习过程和环境中的多个因素。作为一般结果的推论，我们还给出了针对贝叶斯迁移学习及ε-邻域内分布偏移的特定认知误差界。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。