Posterior contraction in Gaussian process regression using Wasserstein approximations
DOI10.1093/imaiai/iax003zbMath1383.62108arXiv1502.02336OpenAlexW2963616939MaRDI QIDQ4603714
Anirban Bhattacharya, Debdeep Pati
Publication date: 19 February 2018
Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1502.02336
Gaussian processkernel regressionHermite polynomialsrandom designWasserstein distanceposterior contraction
Nonparametric regression and quantile regression (62G08) Gaussian processes (60G15) Asymptotic properties of nonparametric inference (62G20) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Bernstein-von Mises theorems for Gaussian regression with increasing number of regressors
- User-friendly tail bounds for sums of random matrices
- Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
- Posterior consistency of Gaussian process prior for nonparametric binary regression
- Rates of contraction of posterior distributions based on Gaussian process priors
- A class of Wasserstein metrics for probability distributions
- Metric entropy and the small ball problem for Gaussian measures
- Approximation, metric entropy and small ball estimates for Gaussian measures
- Model selection for Gaussian regression with random design
- Convergence rates of posterior distributions.
- Asymptotic equivalence theory for nonparametric regression with random design
- Small ball probabilities for Gaussian processes with stationary increments under Hölder norms
- Lower bounds for posterior rates with Gaussian process priors
- Inequalities for modified Bessel functions and their integrals
- On posterior consistency in nonparametric regression problems
- Bayesian inference with rescaled Gaussian process priors
- Anisotropic function estimation using multi-bandwidth Gaussian processes
- Optimal Bayesian estimation in random covariate design with a rescaled Gaussian process prior
- Positive Definite Matrices
- On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
- Information Consistency of Nonparametric Gaussian Process Methods
- Probability
This page was built for publication: Posterior contraction in Gaussian process regression using Wasserstein approximations