Nonstationary Gaussian Process Regression using a Latent Extension of the Input Space
Tobias Pfingsten, Malte Kuß, Carl Edward Rasmussen · 2006
Introduction Gaussian Processes (GPs) can be used to specify a prior over latent functions in non-parametric Bayesian models, e.g. for regression and classification. For this abstract we assume familiarity with the basic concepts of Gaussian Process models, see for example the introduction by Mackay [1]. A GP is defined by a mean and a covariance function, the latter describing dependencies ˆ k(x, x ′ ) = cov(f(x), f(x ′)) between function