区分深度学习预测中数据稀缺与模型不确定性，提升实际应用可靠性。
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
- 用线性化估计器分解模型的两种不确定性来源
- 实验证明不同测试点受两类不确定性的差异影响
- 适合关注模型可信度与鲁棒性的研究人员
我们将两种经典的统计估计器适配到现代深度学习中，以更清晰地揭示预测不确定性来自两个来源：偶然不确定性（由局部数据稀疏引起）和认知不确定性。该方法利用近似费雪信息矩阵的最新进展，使估计可扩展至真实网络架构。实验结果表明，每个测试点受这两种不确定性的影响程度不同，凸显了所提估计器在提升实际应用鲁棒性方面的实用价值。
原文摘要 · Abstract (English)
We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data. Our approach leverages recent advances in approximate Fisher Information Matrices, to enable scaling to actual architectures. Experimental results demonstrate how each test points is differentially impacted by both sources, highlighting the practical utility of our estimators in improving the robustness of real-world applications.
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。