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 and uses said bounds 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 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, Pendulum-v0, Hopper-v2, Ant-v2 and Humanoid-v2. For each experimental setting, an Active Learning framework was applied to demonstrate the advantages of PaiDEs for epistemic uncertainty estimation.

翻译：本文提出了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。该方法利用模型组件间的成对距离建立熵的界限，并将这些界限作为信息准则的估计值。与近期依赖基于样本的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能够在更大空间（高达100倍）内以快100倍的速度估计认知不确定性，并在高维空间中实现更精准的估计。为验证本方法，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、Pendulum-v0、Hopper-v2、Ant-v2和Humanoid-v2环境。针对每个实验场景，均采用主动学习框架以展示PaiDEs在认知不确定性估计中的优势。