Gaussian process interpolation with conformal prediction: methods and comparative analysis

TL;DR

This paper explores the integration of conformal prediction with Gaussian process interpolation to improve the calibration of uncertainty estimates, comparing various CP methods and introducing a new asymmetric score variant.

Contribution

It introduces a novel conformal prediction variant based on an asymmetric score for Gaussian process interpolation, enhancing calibration of prediction intervals.

Findings

CP methods improve calibration of GP prediction intervals

The new asymmetric score variant outperforms existing CP methods

Calibration improvements do not reduce the accuracy of GP predictions

Abstract

This article advocates the use of conformal prediction (CP) methods for Gaussian process (GP) interpolation to enhance the calibration of prediction intervals. We begin by illustrating that using a GP model with parameters selected by maximum likelihood often results in predictions that are not optimally calibrated. CP methods can adjust the prediction intervals, leading to better uncertainty quantification while maintaining the accuracy of the underlying GP model. We compare different CP variants and introduce a novel variant based on an asymmetric score. Our numerical experiments demonstrate the effectiveness of CP methods in improving calibration without compromising accuracy. This work aims to facilitate the adoption of CP methods in the GP community.