用于丰富随机不确定性与认知不确定性建模的归一化流集成
Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling
AI总结：
本研究提出基于固定dropout掩码的归一化流集成方法，利用NF基分布无采样估计随机不确定性并推导微分熵无偏估计，在多个基准实验中验证了其同时精准捕捉两类不确定性的优势。
摘要：
在本研究中，我们展示了如何可靠地估计认知不确定性，同时保持捕捉复杂随机分布所需的灵活性。为此，我们提出了一种归一化流（Normalizing Flow, NF）集成方法，NF是当前建模随机不确定性的最优方法。该集成通过多组固定dropout掩码构建，成本低于单独训练多个NF模型。我们展示了如何利用NF的独特结构——基分布——无需依赖采样即可估计随机不确定性，提供了全面的基准集，并推导了微分熵的无偏估计。我们将这些方法应用于一系列常用于基准测试随机与认知不确定性估计的实验：一维正弦数据、二维有风网格世界（Wet Chicken）、Pendulum以及Hopper。在这些实验中，我们搭建了主动学习框架，评估了每个模型衡量随机与认知不确定性的能力。结果表明，NF集成在捕捉复杂随机不确定性的同时，还能保持准确的认知不确定性估计，具有显著优势。
英文摘要：
In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are state-of-the-art in modeling aleatoric uncertainty. The ensembles are created via sets of fixed dropout masks, making them less expensive than creating separate NF models. We demonstrate how to leverage the unique structure of NFs, base distributions, to estimate aleatoric uncertainty without relying on samples, provide a comprehensive set of baselines, and derive unbiased estimates for differential entropy. The methods were applied to a variety of experiments, commonly used to benchmark aleatoric and epistemic uncertainty estimation: 1D sinusoidal data, 2D windy grid-world ($\it{Wet Chicken}$), $\it{Pendulum}$, and $\it{Hopper}$. In these experiments, we setup an active learning framework and evaluate each model's capability at measuring aleatoric and epistemic uncertainty. The results show the advantages of using NF ensembles in capturing complicated aleatoric while maintaining accurate epistemic uncertainty estimates.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
