Posterior contraction in Gaussian process regression using Wasserstein approximations

DOI10.1093/IMAIAI/IAX003zbMATH Open1383.62108arXiv1502.02336OpenAlexW2963616939MaRDI QIDQ4603714FDOQ4603714

Anirban Bhattacharya, Debdeep Pati

Publication date: 19 February 2018

Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Abstract: We study posterior rates of contraction in Gaussian process regression with unbounded covariate domain. Our argument relies on developing a Gaussian approximation to the posterior of the leading coefficients of a Karhunen--Lo'{e}ve expansion of the Gaussian process. The salient feature of our result is deriving such an approximation in the $L^2$ Wasserstein distance and relating the speed of the approximation to the posterior contraction rate using a coupling argument. Specific illustrations are provided for the Gaussian or squared-exponential covariance kernel.

Full work available at URL: https://arxiv.org/abs/1502.02336

zbMATH Keywords

kernel regressionGaussian processWasserstein distanceposterior contractionHermite polynomialsrandom design

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Gaussian processes (60G15) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• On posterior consistency in nonparametric regression problems
• Anisotropic function estimation using multi-bandwidth Gaussian processes
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• Convergence rates of posterior distributions.
• Probability
• A class of Wasserstein metrics for probability distributions
• User-friendly tail bounds for sums of random matrices
• Asymptotic equivalence theory for nonparametric regression with random design
• Lower bounds for posterior rates with Gaussian process priors
• Rates of contraction of posterior distributions based on Gaussian process priors
• Inequalities for modified Bessel functions and their integrals
• On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
• Bernstein-von Mises theorems for Gaussian regression with increasing number of regressors
• Posterior consistency of Gaussian process prior for nonparametric binary regression
• Model selection for Gaussian regression with random design
• Positive Definite Matrices
• Metric entropy and the small ball problem for Gaussian measures
• Approximation, metric entropy and small ball estimates for Gaussian measures
• Bayesian inference with rescaled Gaussian process priors
• Optimal Bayesian estimation in random covariate design with a rescaled Gaussian process prior
• Information Consistency of Nonparametric Gaussian Process Methods
• Small ball probabilities for Gaussian processes with stationary increments under Hölder norms

Cited In (1)

• Projected Wasserstein Gradient Descent for High-Dimensional Bayesian Inference

This page was built for publication: Posterior contraction in Gaussian process regression using Wasserstein approximations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4603714)