Convergence properties of the expected improvement algorithm with fixed mean and covariance functions - CentraleSupélec Access content directly
Journal Articles Journal of Statistical Planning and Inference Year : 2010

Convergence properties of the expected improvement algorithm with fixed mean and covariance functions

Abstract

This paper deals with the convergence of the expected improvement algorithm, a popular global optimization algorithm based on a Gaussian process model of the function to be optimized. The first result is that under some mild hypotheses on the covariance function k of the Gaussian process, the expected improvement algorithm produces a dense sequence of evaluation points in the search domain, when the function to be optimized is in the reproducing kernel Hilbert space generated by k. The second result states that the density property also holds for P-almost all continuous functions, where P is the (prior) probability distribution induced by the Gaussian process.
Fichier principal
Vignette du fichier
note.pdf (124.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00217562 , version 1 (19-05-2010)

Identifiers

Cite

Emmanuel Vazquez, Julien Bect. Convergence properties of the expected improvement algorithm with fixed mean and covariance functions. Journal of Statistical Planning and Inference, 2010, 140 (11), pp.3088-3095. ⟨10.1016/j.jspi.2010.04.018⟩. ⟨hal-00217562⟩
362 View
1796 Download

Altmetric

Share

Gmail Facebook X LinkedIn More