The correlated knowledge gradient for simulation optimization of continuous parameters using gaussian process regression

Warren Scott, Peter Frazier, Warren Powell

Research output: Contribution to journalArticle

66 Scopus citations

Abstract

We extend the concept of the correlated knowledge-gradient policy for the ranking and selection of a finite set of alternatives to the case of continuous decision variables. We propose an approximate knowledge gradient for problems with continuous decision variables in the context of a Gaussian process regression model in a Bayesian setting, along with an algorithm to maximize the approximate knowledge gradient. In the problem class considered, we use the knowledge gradient for continuous parameters to sequentially choose where to sample an expensive noisy function in order to find the maximum quickly. We show that the knowledge gradient for continuous decisions is a generalization of the efficient global optimization algorithm proposed in [D. R. Jones, M. Schonlau, and W. J. Welch, J. Global Optim., 13 (1998), pp. 455-492].

Original languageEnglish (US)
Pages (from-to)996-1026
Number of pages31
JournalSIAM Journal on Optimization
Volume21
Issue number3
DOIs
StatePublished - Oct 24 2011

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science

Keywords

  • Bayesian global optimization
  • Expected improvement
  • Gaussian process regression
  • Knowledge gradient
  • Model calibration

Fingerprint Dive into the research topics of 'The correlated knowledge gradient for simulation optimization of continuous parameters using gaussian process regression'. Together they form a unique fingerprint.

  • Cite this