In machine learning, the ability to assess uncertainty in model predictions is crucial for decision-making, safety-critical applications, and model generalizability. This work introduces a novel approach for epistemic uncertainty estimation for ensemble models using pairwise-distance estimators (PaiDEs). These estimators utilize the pairwise-distance between model components to establish bounds on entropy, which are then used as estimates for information-based criterion. Unlike recent deep learning methods for epistemic uncertainty estimation, which rely on sample-based Monte Carlo estimators, PaiDEs are able to estimate epistemic uncertainty up to 100 times faster, over a larger input space (up to 100 times) and perform more accurately in higher dimensions. To validate our approach, we conducted a series of experiments commonly used to evaluate epistemic uncertainty estimation: 1D sinusoidal data, $\textit{Pendulum-v0}$, $\textit{Hopper-v2}$, $\textit{Ant-v2}$ and $\textit{Humanoid-v2}$. For each experimental setting, an Active Learning framework was applied to demonstrate the advantages of PaiDEs for epistemic uncertainty estimation.

翻译：在机器学习中，评估模型预测的不确定性对于决策、安全关键应用及模型泛化能力至关重要。本文提出一种基于成对距离估计器（PaiDEs）的集成模型认知不确定性估计新方法。这些估计器利用模型组件间的成对距离建立熵的界限，进而将其作为基于信息准则的估计值。与近期依赖样本蒙特卡洛估计器的深度学习认知不确定性估计方法不同，PaiDEs能够在对更大输入空间（最高100倍）上实现快达100倍的认知不确定性估计速度，并在高维空间中保持更高精度。为验证该方法的有效性，我们开展了一系列常用于评估认知不确定性估计的实验：一维正弦数据、$\textit{Pendulum-v0}$、$\textit{Hopper-v2}$、$\textit{Ant-v2}$及$\textit{Humanoid-v2}$。针对每个实验设置，均采用主动学习框架来展示PaiDEs在认知不确定性估计中的优势。