Distribution Calibration for Regression
This addresses uncertainty quantification in regression for fields like statistics and machine learning, but it is incremental as it builds on existing calibration concepts.
The paper tackles the problem of obtaining well-calibrated output distributions from regression models to quantify prediction uncertainty, introducing distribution calibration and a post-hoc method using multi-output Gaussian Processes with a Beta link function, which shows improvements in calibration metrics.
We are concerned with obtaining well-calibrated output distributions from regression models. Such distributions allow us to quantify the uncertainty that the model has regarding the predicted target value. We introduce the novel concept of distribution calibration, and demonstrate its advantages over the existing definition of quantile calibration. We further propose a post-hoc approach to improving the predictions from previously trained regression models, using multi-output Gaussian Processes with a novel Beta link function. The proposed method is experimentally verified on a set of common regression models and shows improvements for both distribution-level and quantile-level calibration.