Fast Computation of the Multi-points Expected Improvement with Applications in Batch Selection

Abstract : The Multipoint Expected Improvement criterion (or q-EI) has recently been studied in batch-sequential Bayesian Optimization. This paper deals with the new way of computing q-EI, without usingMonte-Carlo simulations, through a new closed form formula. The latter allows a very fast computation of q-EI for reasonably low values of q (typically, less than 10). New parallel kriging-based optimization strategies, tested on various toy examples, show promising results.
Liste complète des métadonnées

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00732512
Contributor : David Ginsbourger <>
Submitted on : Friday, October 12, 2012 - 5:56:09 PM
Last modification on : Thursday, January 11, 2018 - 6:22:26 AM
Document(s) archivé(s) le : Saturday, December 17, 2016 - 12:34:45 AM

File

CC_DG_MultipointEI_LION7_2_.pd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00732512, version 2

Collections

Citation

Clément Chevalier, David Ginsbourger. Fast Computation of the Multi-points Expected Improvement with Applications in Batch Selection. 2012. ⟨hal-00732512v2⟩

Share

Metrics

Record views

679

Files downloads

1617