Posterior contraction for deep Gaussian process priors

arXiv2105.07410MaRDI QIDQ6367752FDOQ6367752

Johannes Schmidt-Hieber, Gianluca Finocchio

Publication date: 16 May 2021

Abstract: We study posterior contraction rates for a class of deep Gaussian process priors applied to the nonparametric regression problem under a general composition assumption on the regression function. It is shown that the contraction rates can achieve the minimax convergence rate (up to $logn$ factors), while being adaptive to the underlying structure and smoothness of the target function. The proposed framework extends the Bayesian nonparametric theory for Gaussian process priors.

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Statistical aspects of big data and data science (62R07) Minimax procedures in statistical decision theory (62C20)

This page was built for publication: Posterior contraction for deep Gaussian process priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6367752)