Generative diffusion models, notable for their large parameter count
(exceeding 100 million) and operation within high-dimensional image spaces,
pose significant challenges for traditional uncertainty estimation methods due
to computational demands. In this work, we introduce an innovative framework,
Diffusion Ensembles for Capturing Uncertainty (DECU), designed for estimating
epistemic uncertainty for diffusion models. The DECU framework introduces a
novel method that efficiently trains ensembles of conditional diffusion models
by incorporating a static set of pre-trained parameters, drastically reducing
the computational burden and the number of parameters that require training.
Additionally, DECU employs Pairwise-Distance Estimators (PaiDEs) to accurately
measure epistemic uncertainty by evaluating the mutual information between
model outputs and weights in high-dimensional spaces. The effectiveness of this
framework is demonstrated through experiments on the ImageNet dataset,
highlighting its capability to capture epistemic uncertainty, specifically in
under-sampled image classes.

Diffusion Ensembles for Capturing Uncertainty (DECU) is an innovative framework designed to estimate epistemic uncertainty in generative diffusion models by efficiently training ensembles of conditional diffusion models with a static set of pre-trained parameters and employing Pairwise-Distance Estimators (PaiDEs) to accurately measure epistemic uncertainty in high-dimensional spaces.

揭示大型生成网络的光芒：扩散模型中估计认识不确定性

Shedding Light on Large Generative Networks: Estimating Epistemic  Uncertainty in Diffusion Models

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.

该研究引入了一种新颖的方法，使用成对距离评估器（PaiDEs）对集成模型进行认识不确定性估计，这些评估器利用模型组件之间的成对距离建立熵的上下界，并使用这些界限作为信息准则的估计值。与最近的深度学习方法不同，这些方法依赖于基于样本的蒙特卡洛估计器，PaiDEs 能够以高达 100 倍的速度，覆盖更大空间（高达 100 倍），在更高维度上实现更准确的认识不确定性估计。为了验证我们的方法，我们进行了一系列常用于评估认识不确定性估计的实验：1D 正弦数据，Pendulum-v0，Hopper-v2，Ant-v2 和 Humanoid-v2。基于每个实验环境，应用主动学习框架来展示 PaiDEs 在认识不确定性估计方面的优势。