Affordable Access

deepdyve-link
Publisher Website

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

Authors
  • Vazquez, Emmanuel
  • Bect, Julien
Publication Date
Nov 01, 2010
Identifiers
DOI: 10.1016/j.jspi.2010.04.018
OAI: oai:HAL:hal-00217562v1
Source
HAL
Keywords
Language
English
License
Unknown
External links

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.

Report this publication

Statistics

Seen <100 times