Properties of the Bayesian Parameter Estimation of a Regression Based on Gaussian Processes

Download insert_drive_file

Authors:

Burnaev E., Zaytsev A., Spokoiny V.

Journal / Event:

To be published in Journal of Fundamental and Applied Mathematics

Abstract:

We consider the regression approach based on Gaussian processes and outline our theoretical results about the properties of the posterior distribution of the corresponding covariance function’s parameter vector. We perform statistical experiments confirming that the obtained theoretical propositions are valid for a wide class of covariance functions, commonly used in applied problems.

Keywords: Approximation, Gaussian Processes