Posterior consistency of Gaussian process prior for nonparametric binary regression

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.

Published at http://dx.doi.org/10.1214/009053606000000795 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (1)

• New approaches to Bayesian consistency

Cited by in corpus (10)

• Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
• Rates of contraction of posterior distributions based on Gaussian process priors
• Adaptive Bayesian estimation using a Gaussian random field with inverse Gamma bandwidth
• Posterior consistency of nonparametric conditional moment restricted models
• Personalized Optimization with User's Feedback
• Bayesian nonparametric estimation and consistency of mixed multinomial logit choice models
• Nonparametric Bayes modeling of count processes
• Multi-Agent Safe Planning with Gaussian Processes
• A Fast and Calibrated Computer Model Emulator: An Empirical Bayes Approach
• Zeros of Gaussian Weyl-Heisenberg functions and hyperuniformity of charge