Posterior consistency of Gaussian process prior for nonparametric binary regression

DOI10.1214/009053606000000795zbMATH Open1106.62039arXivmath/0702686OpenAlexW3098799846MaRDI QIDQ869978FDOQ869978

Authors: Subhashis Ghosal, Anindya Roy 

Publication date: 12 March 2007

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Consider binary observations whose response probability is an unknown smooth function of a set of covariates. Suppose that a prior on the response probability function is induced by a Gaussian process mapped to the unit interval through a link function. In this paper we study consistency of the resulting posterior distribution. If the covariance kernel has derivatives up to a desired order and the bandwidth parameter of the kernel is allowed to take arbitrarily small values, we show that the posterior distribution is consistent in the $L_1$-distance. As an auxiliary result to our proofs, we show that, under certain conditions, a Gaussian process assigns positive probabilities to the uniform neighborhoods of a continuous function. This result may be of independent interest in the literature for small ball probabilities of Gaussian processes.

Full work available at URL: https://arxiv.org/abs/math/0702686

Recommendations

• Alternative posterior consistency results in nonparametric binary regression using Gaussian process priors
• Posterior consistency of logistic Gaussian process priors in density estimation
• On posterior consistency in nonparametric regression problems
• Rates of contraction of posterior distributions based on Gaussian process priors
• Nonparametric binary regression using a Gaussian process prior

zbMATH Keywords

reproducing kernel Hilbert spacemaximal inequalityKarhunen-Loeve expansionentropy boundsHoeffding's inequality

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Inference from stochastic processes (62M99) Applications of functional analysis in probability theory and statistics (46N30)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• The Logistic Normal Distribution for Bayesian, Nonparametric, Predictive Densities
• Title not available (Why is that?)
• On posterior consistency in nonparametric regression problems
• Bayesian Estimation of the Spectral Density of a Time Series
• Probability Inequalities for Sums of Bounded Random Variables
• Title not available (Why is that?)
• Convergence rates of posterior distributions.
• Posterior consistency of Dirichlet mixtures in density estimation
• New approaches to Bayesian consistency
• Posterior consistency of logistic Gaussian process priors in density estimation
• Nonparametric binary regression using a Gaussian process prior
• Title not available (Why is that?)

Cited In (51)

• A Nonstationary Soft Partitioned Gaussian Process Model via Random Spanning Trees
• High-dimensional Bayesian network classification with network global-local shrinkage priors
• Adaptive rates of contraction of posterior distributions in Bayesian wavelet regression
• Information rates of nonparametric Gaussian process methods
• Posterior contraction in Gaussian process regression using Wasserstein approximations
• \texttt{CAMERA}: a method for cost-aware, adaptive, multifidelity, efficient reliability analysis
• A Gaussian process regression approach to a single-index model
• On asymptotic properties of Bayesian partially linear models
• On posterior distribution of Bayesian wavelet thresholding
• Convergence of posterior distribution in the mixture of regressions
• Asymptotic properties of posterior distributions in nonparametric regression with non-Gaussian errors
• Nonparametric Bayes classification and hypothesis testing on manifolds
• Bayesian nonparametric regression with varying residual density
• Consistency of posterior distributions for heteroscedastic nonparametric regression models
• Rates of contraction of posterior distributions based on Gaussian process priors
• On posterior consistency in nonparametric regression problems
• Nonparametric binary regression using a Gaussian process prior
• Posterior contraction rates for stochastic block models
• Zeros of Gaussian Weyl-Heisenberg functions and hyperuniformity of charge
• Generalized Gaussian process regression model for non-Gaussian functional data
• On Bayesian quantile regression using a pseudo-joint asymmetric Laplace likelihood
• Sup-Hellinger consistency for local density regression
• Bayesian consistency for Markov models
• Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics
• Posterior consistency of nonparametric conditional moment restricted models
• Posterior convergence for Bayesian functional linear regression
• Optimal Bayesian estimation in random covariate design with a rescaled Gaussian process prior
• Bayesian nonparametric estimation and consistency of mixed multinomial logit choice models
• Locally adaptive Bayes nonparametric regression via nested Gaussian processes
• Alternative posterior consistency results in nonparametric binary regression using Gaussian process priors
• Posterior consistency for Gaussian process approximations of Bayesian posterior distributions
• Penalized Gaussian process regression and classification for high-dimensional nonlinear data
• Modeling volatility for high-frequency data with rounding error: a nonparametric Bayesian approach
• Identifying Nonlinear Dynamics with High Confidence from Sparse Data
• Personalized optimization with user's feedback
• Moderate deviations inequalities for Gaussian process regression
• Hypotheses testing and posterior concentration rates for semi-Markov processes
• A note on Bayesian nonparametric regression function estimation
• Posterior consistency of random effects models for binary data
• Propriety of the reference posterior distribution in Gaussian process modeling
• Posterior consistency of logistic Gaussian process priors in density estimation
• Adaptive Bayesian procedures using random series priors
• A fast and calibrated computer model emulator: an empirical Bayes approach
• Active Learning for Enumerating Local Minima Based on Gaussian Process Derivatives
• Title not available (Why is that?)
• Bayesian classification, anomaly detection, and survival analysis using network inputs with application to the microbiome
• Gaussian approximation of general non-parametric posterior distributions
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• A nonparametric Bayesian methodology for regression discontinuity designs
• A direct approach to understanding posterior consistency of Bayesian regression problems
• Bayesian Spatial Blind Source Separation via the Thresholded Gaussian Process

This page was built for publication: Posterior consistency of Gaussian process prior for nonparametric binary regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q869978)