论文标题
单个确定性神经网络的非参数不确定性定量
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
论文作者
论文摘要
本文提出了一种快速可扩展的方法，用于对机器学习模型的预测进行不确定性量化。首先，我们展示了基于Nadaraya-Watson对条件标签分布的非参数估计的分类器预测不确定性的原则方法。重要的是，所提出的方法允许清除明确的态度和认知不确定性。结果方法直接在特征空间中起作用。但是，通过考虑网络引起的数据的嵌入，可以将其应用于任何神经网络。我们证明了该方法在文本分类问题的不确定性估计任务以及各种现实世界图像数据集中的强劲性能，例如MNIST，SVHN，CIFAR-100和几个版本的ImageNet。
This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions. First, we show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. Importantly, the proposed approach allows to disentangle explicitly aleatoric and epistemic uncertainties. The resulting method works directly in the feature space. However, one can apply it to any neural network by considering an embedding of the data induced by the network. We demonstrate the strong performance of the method in uncertainty estimation tasks on text classification problems and a variety of real-world image datasets, such as MNIST, SVHN, CIFAR-100 and several versions of ImageNet.
