提出回归任务中严谨的频率派不确定性估计方法
Do you understand epistemic uncertainty? Think again! Rigorous frequentist epistemic uncertainty estimation in regression
- 通过自回归反馈机制生成条件预测，捕捉模型不确定性
- 首次实现回归场景下频率派认知不确定性严格量化
- 仅需微小架构改动，适合部署在现有回归模型中
准确量化模型不确定性对理解预测可靠性至关重要，但区分偶然不确定性与认知不确定性仍具挑战。本文将近期分类任务中的方法拓展至回归场景，提出一种新颖的频率派认知与偶然不确定性估计方法。通过将模型初始输出作为额外输入反馈回模型，构建条件预测机制，从而通过观察预测响应随自身历史输出的变化来严格测量不确定性。本文建立了完整的理论框架，用于在频率派范式下分析回归任务中的认知不确定性，并说明如何在实践中利用该方法评估模型置信度，且对原始模型架构改动极小。
原文摘要 · Abstract (English)
Quantifying model uncertainty is critical for understanding prediction reliability, yet distinguishing between aleatoric and epistemic uncertainty remains challenging. We extend recent work from classification to regression to provide a novel frequentist approach to epistemic and aleatoric uncertainty estimation. We train models to generate conditional predictions by feeding their initial output back as an additional input. This method allows for a rigorous measurement of model uncertainty by observing how prediction responses change when conditioned on the model's previous answer. We provide a complete theoretical framework to analyze epistemic uncertainty in regression in a frequentist way, and explain how it can be exploited in practice to gauge a model's uncertainty, with minimal changes to the original architecture.
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。