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.
Description
[1904.01383] Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel?
%0 Journal Article
%1 hadji2019trust
%A Hadji, Amine
%A Szábo, Botond
%D 2019
%K bayesian gaussian-proceses uncertainty
%T Can we trust Bayesian uncertainty quantification from Gaussian process
priors with squared exponential covariance kernel?
%U http://arxiv.org/abs/1904.01383
%X 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.
@article{hadji2019trust,
abstract = {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.},
added-at = {2019-08-07T22:01:03.000+0200},
author = {Hadji, Amine and Szábo, Botond},
biburl = {https://www.bibsonomy.org/bibtex/205b7e5ef50716c3cba689ba9067cacea/kirk86},
description = {[1904.01383] Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel?},
interhash = {e871aca694b2f9a0099f6f8d1f0f8d81},
intrahash = {05b7e5ef50716c3cba689ba9067cacea},
keywords = {bayesian gaussian-proceses uncertainty},
note = {cite arxiv:1904.01383},
timestamp = {2019-08-07T22:01:03.000+0200},
title = {Can we trust Bayesian uncertainty quantification from Gaussian process
priors with squared exponential covariance kernel?},
url = {http://arxiv.org/abs/1904.01383},
year = 2019
}