Translator Disclaimer
2007 Bayesian inference with rescaled Gaussian process priors
Aad van der Vaart, Harry van Zanten
Electron. J. Statist. 1(none): 433-448 (2007). DOI: 10.1214/07-EJS098

Abstract

We use rescaled Gaussian processes as prior models for functional parameters in nonparametric statistical models. We show how the rate of contraction of the posterior distributions depends on the scaling factor. In particular, we exhibit rescaled Gaussian process priors yielding posteriors that contract around the true parameter at optimal convergence rates. To derive our results we establish bounds on small deviation probabilities for smooth stationary Gaussian processes.

Citation

Download Citation

Aad van der Vaart. Harry van Zanten. "Bayesian inference with rescaled Gaussian process priors." Electron. J. Statist. 1 433 - 448, 2007. https://doi.org/10.1214/07-EJS098

Information

Published: 2007
First available in Project Euclid: 22 October 2007

zbMATH: 1140.62066
MathSciNet: MR2357712
Digital Object Identifier: 10.1214/07-EJS098

Subjects:
Primary: 62C10, 62G05
Secondary: 60G15

Rights: Copyright © 2007 The Institute of Mathematical Statistics and the Bernoulli Society

JOURNAL ARTICLE
16 PAGES


SHARE
Back to Top