Nonparametric Uncertainty Quantification for Single Deterministic Neural Network

Nikita Yurevich Kotelevskii, Aleksandr Artemenkov, Kirill Fedyanin, Fedor Noskov, Alexander Fishkov, Artem Shelmanov, Artem Vazhentsev, Aleksandr Petiushko, Maxim Panov

Keywords: Uncertainty Quantification, Nonparametric Methods, Deep Learning, Machine Learning

TL;DR: New nonparametric uncertainty quantification for single deterministic neural network.

Abstract: 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 approach allows to disentangle explicitly \textit{aleatoric} and \textit{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.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2202.03101/code)