← Search

Kirill Fedyanin

2 accepted papers

2022

Nonparametric Uncertainty Quantification for Single Deterministic Neural Network

NeurIPS 2022accept

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.…

2022

Uncertainty Estimation of Transformer Predictions for Misclassification Detection

ACL 2022long

Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc. Most of the works on modeling the uncertainty of deep neural networks evaluate these metho…