Temperature Scaling for Quantile Calibration

Abstract

Deep learning models are often poorly calibrated, i.e., they may produce overconfident predictions that are wrong, implying that their uncertainty estimates are unreliable. While a number of approaches have been proposed recently to calibrate classification models, relatively little work exists on calibrating regression models. Temperature Scaling is one of the most popular methods for classification calibration. It performs better than or equal to more sophisticated methods. We investigate the use of Temperature Scaling for regression calibration under notion of quantile calibration.

Tasks

Reproductions