Expected Improvement in Efficient Global Optimization Through Bootstrapped Kriging - Replaced by CentER DP 2011-015

Jack P.C. Kleijnen, W.C.M. van Beers, I. van Nieuwenhuyse

Research output: Working paperDiscussion paperOther research output

Abstract

This paper uses a sequentialized experimental design to select simulation input com- binations for global optimization, based on Kriging (also called Gaussian process or spatial correlation modeling); this Kriging is used to analyze the input/output data of the simulation model (computer code). This paper adapts the classic "ex- pected improvement" (EI) in "efficient global optimization" (EGO) through the introduction of an unbiased estimator of the Kriging predictor variance; this estima- tor uses parametric bootstrapping. Classic EI and bootstrapped EI are compared through four popular test functions, including the six-hump camel-back and two Hartmann functions. These empirical results demonstrate that in some applications bootstrapped EI finds the global optimum faster than classic EI does; in general, however, the classic EI may be considered to be a robust global optimizer.
Original languageEnglish
Place of PublicationTilburg
PublisherOperations research
Number of pages17
Volume2010-62
Publication statusPublished - 2010

Publication series

NameCentER Discussion Paper
Volume2010-62

Keywords

  • Simulation
  • Optimization
  • Kriging
  • Bootstrap

Fingerprint Dive into the research topics of 'Expected Improvement in Efficient Global Optimization Through Bootstrapped Kriging - Replaced by CentER DP 2011-015'. Together they form a unique fingerprint.

  • Cite this

    Kleijnen, J. P. C., van Beers, W. C. M., & van Nieuwenhuyse, I. (2010). Expected Improvement in Efficient Global Optimization Through Bootstrapped Kriging - Replaced by CentER DP 2011-015. (CentER Discussion Paper; Vol. 2010-62). Operations research.