Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel?

04/02/2019
by   Amine Hadji, et al.
0

We investigate the frequentist coverage properties of credible sets resulting in from Gaussian process priors with squared exponential covariance kernel. First we show that by selecting the scaling hyper-parameter using the maximum marginal likelihood estimator in the (slightly modified) squared exponential covariance kernel the corresponding credible sets will provide overconfident, misleading uncertainty statements for a large, representative subclass of the functional parameters in context of the Gaussian white noise model. Then we show that by either blowing up the credible sets with a logarithmic factor or modifying the maximum marginal likelihood estimator with a logarithmic term one can get reliable uncertainty statement and adaptive size of the credible sets under some additional restriction. Finally we demonstrate on a numerical study that the derived negative and positive results extend beyond the Gaussian white noise model to the nonparametric regression and classification models for small sample sizes as well.

READ FULL TEXT
research
01/29/2020

Maximum likelihood estimation and uncertainty quantification for Gaussian process approximation of deterministic functions

Despite the ubiquity of the Gaussian process regression model, few theor...
research
10/06/2021

Estimation of the Scale Parameter for a Misspecified Gaussian Process Model

Parameters of the covariance kernel of a Gaussian process model often ne...
research
05/06/2022

Optimal recovery and uncertainty quantification for distributed Gaussian process regression

Gaussian Processes (GP) are widely used for probabilistic modeling and i...
research
08/15/2019

On identifiability and consistency of the nugget in Gaussian spatial process models

Spatial process models popular in geostatistics often represent the obse...
research
12/19/2019

Integrated Emulators for Systems of Computer Models

We generalize the state-of-the-art linked emulator for a system of two c...
research
10/16/2019

Multiscale Analysis of Bayesian CART

This paper affords new insights about Bayesian CART in the context of st...
research
09/13/2022

Adaptive inference over Besov spaces in the white noise model using p-exponential priors

In many scientific applications the aim is to infer a function which is ...

Please sign up or login with your details

Forgot password? Click here to reset