Skip to yearly menu bar Skip to main content


Sharp Calibrated Gaussian Processes

Alexandre Capone · Sandra Hirche · Geoff Pleiss · Geoff Pleiss

Great Hall & Hall B1+B2 (level 1) #1025
[ ]
[ Paper [ Slides [ Poster [ OpenReview
Thu 14 Dec 3 p.m. PST — 5 p.m. PST


While Gaussian processes are a mainstay for various engineering and scientific applications, the uncertainty estimates don't satisfy frequentist guarantees and can be miscalibrated in practice. State-of-the-art approaches for designing calibrated models rely on inflating the Gaussian process posterior variance, which yields confidence intervals that are potentially too coarse. To remedy this, we present a calibration approach that generates predictive quantiles using a computation inspired by the vanilla Gaussian process posterior variance but using a different set of hyperparameters chosen to satisfy an empirical calibration constraint. This results in a calibration approach that is considerably more flexible than existing approaches, which we optimize to yield tight predictive quantiles. Our approach is shown to yield a calibrated model under reasonable assumptions. Furthermore, it outperforms existing approaches in sharpness when employed for calibrated regression.

Chat is not available.