Quantifying Epistemic Uncertainty in Binary Classification via Accuracy Gain
Christopher Qian, Tyler Ganter, Joshua Michalenko, Feng Liang, Jason Adams · Statistical Analysis and Data Mining The ASA Data Science Journal · 2024
ABSTRACT Recently, a surge of interest has been given to quantifying epistemic uncertainty (EU), the reducible portion of uncertainty due to lack of data. We propose a novel EU estimator in the binary classification setting, as the posterior expected value of the empirical gain in accuracy between the current prediction and the optimal prediction. In order to validate the performance of our EU estimator, we introduce an experimental procedure where we take an existing dataset, remove a set of points, and compare the estimated EU with the observed change in accuracy. Through real and simulated data experiments, we demonstrate the effectiveness of our proposed EU estimator.