Gaussian process optimization with failures: classification and convergence proof - Archive ouverte HAL Access content directly
Journal Articles Journal of Global Optimization Year : 2020

Gaussian process optimization with failures: classification and convergence proof

Abstract

We consider the optimization of a computer model where each simulation either fails or returns a valid output performance. We first propose a new joint Gaussian process model for classification of the inputs (computation failure or success) and for regression of the performance function. We provide results that allow for a computationally efficient maximum likelihood estimation of the covariance parameters, with a stochastic approximation of the likelihood gradient. We then extend the classical improvement criterion to our setting of joint classification and regression. We provide an efficient computation procedure for the extended criterion and its gradient. We prove the almost sure convergence of the global optimization algorithm following from this extended criterion. We also study the practical performances of this algorithm, both on simulated data and on a real computer model in the context of automotive fan design.
Fichier principal
Vignette du fichier
optimwithfailurerevised_hal.pdf (448.41 Ko) Télécharger le fichier
Supplementarymaterial.pdf (1.86 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02100819 , version 1 (16-04-2019)
hal-02100819 , version 2 (29-01-2020)

Identifiers

Cite

François Bachoc, Céline Helbert, Victor Picheny. Gaussian process optimization with failures: classification and convergence proof. Journal of Global Optimization, In press, ⟨10.1007/s10898-020-00920-0⟩. ⟨hal-02100819v2⟩
392 View
806 Download

Altmetric

Share

Gmail Facebook X LinkedIn More