Pointwise Consistency of the Kriging Predictor with Known Mean and Covariance Functions
This paper deals with several issues related to the pointwise consistency of the kriging predictor when the mean and the covariance functions are known. These questions are of general importance in the context of computer experiments. The analysis is based on the properties of approximations in reproducing kernel Hilbert spaces. We fix an erroneous claim of Yakowitz and Szidarovszky (J. Multivariate Analysis, 1985) that, under some assumptions, the kriging predictor is pointwise consistent for all continuous sample paths.
KeywordsCovariance Function Sample Path Reproduce Kernel Hilbert Space Lebesgue Constant Bayesian Point
Unable to display preview. Download preview PDF.
- De Marchi, S. and R. Schaback (2008). Stability of kernel-based interpolation. Advances in Computational Mathematics. doi: 10.1007/s10444-008-9093-4.Google Scholar
- Vazquez, E. and J. Bect (2009). On the convergence of the expected improvement algorithm. Preprint available on arXiv, http://arxiv.org/abs/0712.3744v2.
- Villemonteix, J. (2008). Optimisation de Fonctions Coûteuses. Ph. D. thesis, Université Paris-Sud XI, Faculté des Sciences d’Orsay.Google Scholar