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.
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00217562
Contributor : Julien Bect <>
Submitted on : Wednesday, May 19, 2010 - 9:18:34 PM
Last modification on : Thursday, March 29, 2018 - 11:06:04 AM
Long-term archiving on : Thursday, September 16, 2010 - 12:20:29 PM

Files

note.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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

Share

Metrics

Record views

574

Files downloads

1111