Supremum Norm Posterior Contraction and Credible Sets for Nonparametric Multivariate Regression

TL;DR

This paper establishes optimal Bayesian posterior contraction rates and credible sets for nonparametric multivariate regression functions and their derivatives, using tensor product B-splines, covering anisotropic smoothness.

Contribution

It introduces a Bayesian method with tensor product B-splines for estimating multivariate regression functions and derivatives, achieving minimax rates and guaranteed frequentist coverage.

Findings

Posterior contraction rates match minimax bounds.

Credible sets have guaranteed frequentist coverage.

New theoretical results on tensor product B-splines.

Abstract

In the setting of nonparametric multivariate regression with unknown error variance, we study asymptotic properties of a Bayesian method for estimating a regression function f and its mixed partial derivatives. We use a random series of tensor product of B-splines with normal basis coefficients as a prior for f, and the error variance is either estimated using the empirical Bayes approach or is endowed with a suitable prior in a hierarchical Bayes approach. We establish pointwise, L2 and supremum norm posterior contraction rates for f and its mixed partial derivatives, and show that they coincide with the minimax rates. Our results cover even the anisotropic situation, where the true regression function may have different smoothness in different directions. Using the convergence bounds, we show that pointwise, L2 and supremum norm credible sets for f and its mixed partial derivatives have guaranteed frequentist coverage with optimal size. New results on tensor products of B-splines are also obtained in the course.