Global optimization based on noisy evaluations: an empirical study of two statistical approaches - CentraleSupélec Access content directly
Journal Articles Journal of Physics: Conference Series Year : 2008

Global optimization based on noisy evaluations: an empirical study of two statistical approaches

Abstract

The optimization of the output of complex computer codes has often to be achieved with a small budget of evaluations. Algorithms dedicated to such problems have been developed and compared, such as the Expected Improvement algorithm (EI) or the Informational Approach to Global Optimization (IAGO). However, the influence of noisy evaluation results on the outcome of these comparisons has often been neglected, despite its frequent appearance in industrial problems. In this paper, empirical convergence rates for EI and IAGO are compared when an additive noise corrupts the result of an evaluation. IAGO appears more efficient than EI and various modifications of EI designed to deal with noisy evaluations.
Fichier principal
Vignette du fichier
IOP.pdf (31.56 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00278188 , version 1 (13-05-2008)
hal-00278188 , version 2 (17-03-2009)

Identifiers

Cite

Emmanuel Vazquez, Julien Villemonteix, Maryan Sidorkiewicz, Eric Walter. Global optimization based on noisy evaluations: an empirical study of two statistical approaches. Journal of Physics: Conference Series, 2008, 135 (1), pp.012100. ⟨10.1088/1742-6596/135/1/012100⟩. ⟨hal-00278188v2⟩
205 View
228 Download

Altmetric

Share

Gmail Facebook X LinkedIn More