Properties of the Bayesian Parameter Estimation of a Regression Based on Gaussian Processes (in English)
Burnaev E., Zaytsev A., Spokoiny V.
To be published in Journal of Fundamental and Applied Mathematics
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.