重新审视机器学习中的不确定性分类，提出更清晰的理论框架。
Rethinking Aleatoric and Epistemic Uncertainty
- 从决策理论出发，构建更严谨的不确定性分析框架。
- 发现现有信息论指标常误估不确定性，但仍有数据采集指导价值。
- 适合关注模型可信度与可靠性评估的研究者阅读。
机器学习中的随机性不确定性和认知不确定性概念被广泛用于解释概率预测。我们发现现有讨论存在内在不一致，根源在于当前的随机-认知划分无法充分表达研究者关心的所有不确定性类型。为此，本文提出一种基于决策理论的视角，将不确定性、预测性能与数据统计离散性进行严格关联，有助于推动领域更清晰地思考问题。此外，我们揭示了常用的信息论量度在估计其声称目标时表现不佳，但仍可在指导数据收集方面发挥作用。
原文摘要 · Abstract (English)
The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the aleatoric-epistemic view being insufficiently expressive to capture all the distinct quantities that researchers are interested in. To address this we present a decision-theoretic perspective that relates rigorous notions of uncertainty, predictive performance and statistical dispersion in data. This serves to support clearer thinking as the field moves forward. Additionally we provide insights into popular information-theoretic quantities, showing they can be poor estimators of what they are often purported to measure, while also explaining how they can still be useful in guiding data acquisition.
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。