Calibrated bootstrap for uncertainty quantification in regression models
Abstract
Obtaining accurate estimates of machine learning model uncertainties on newly predicted data is essential for understanding the accuracy of the model and whether its predictions can be trusted. A common approach to such uncertainty quantification is to estimate the variance from an ensemble of models, which are often generated by the generally applicable bootstrap method. In this work, we demonstrate that the direct bootstrap ensemble standard deviation is not an accurate estimate of uncertainty and propose a calibration method to dramatically improve its accuracy. We demonstrate the effectiveness of this calibration method for both synthetic data and physical datasets from the field of Materials Science and Engineering. The approach is motivated by applications in physical and biological science but is quite general and should be applicable for uncertainty quantification in a wide range of machine learning regression models.
Cite
@article{arxiv.2105.13303,
title = {Calibrated bootstrap for uncertainty quantification in regression models},
author = {Glenn Palmer and Siqi Du and Alexander Politowicz and Joshua Paul Emory and Xiyu Yang and Anupraas Gautam and Grishma Gupta and Zhelong Li and Ryan Jacobs and Dane Morgan},
journal= {arXiv preprint arXiv:2105.13303},
year = {2021}
}