Expected Improvements for the Asynchronous Parallel Global Optimization of Expensive Functions : Potentials and Challenges - Mines Saint-Étienne Accéder directement au contenu
Article Dans Une Revue Lecture Notes in Computer Science Année : 2012

Expected Improvements for the Asynchronous Parallel Global Optimization of Expensive Functions : Potentials and Challenges

Résumé

Sequential sampling strategies based on Gaussian processes are now widely used for the optimization of problems involving costly simulations. But Gaussian processes can also generate parallel optimiza- tion strategies. We focus here on a new, parameter free, parallel expected improvement criterion for asynchronous optimization. An estimation of the criterion, which mixes Monte Carlo sampling and analytical bounds, is proposed. Logarithmic speed-ups are measured on 1 and 9 dimensional functions.
Fichier non déposé

Dates et versions

emse-00686504 , version 1 (10-04-2012)

Identifiants

Citer

Janis Janusevskis, Rodolphe Le Riche, David Ginsbourger, Ramunas Girdziusas. Expected Improvements for the Asynchronous Parallel Global Optimization of Expensive Functions : Potentials and Challenges. Lecture Notes in Computer Science, 2012, Learning and Intelligent Optimization, pp. 413-418. ⟨10.1007/978-3-642-34413-8_37⟩. ⟨emse-00686504⟩
84 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More