Examples of inconsistency in optimization by expected improvement

DOI10.1007/S10898-012-9936-XMaRDI QIDQ2393071zbMATH OpenOpenAlexFDO

Authors Dmitry Yarotsky

Publication date 7 August 2013

Published in Journal of Global Optimization (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1109.1320

zbMATH Keywords

expected improvementBayesian optimizationanalytic kernelGaussian covariance function

Mathematics Subject Classification ID

Stochastic programming (90C15)

Abstract: We consider the 1D Expected Improvement optimization based on Gaussian processes having spectral densities converging to zero faster than exponentially. We give examples of problems where the optimization trajectory is not dense in the design space. In particular, we prove that for Gaussian kernels there exist smooth objective functions for which the optimization does not converge on the optimum.

Recommendations

• Convergence rates of efficient global optimization algorithms
• Convergence properties of the expected improvement algorithm with fixed mean and covariance functions
• On the convergence rates of expected improvement methods
• Expected improvement for expensive optimization: a review
• A complete expected improvement criterion for Gaussian process assisted highly constrained expensive optimization

Cites work

• scientific article; zbMATH DE number 996424 (Why is no real title available?)
• scientific article; zbMATH DE number 43985 (Why is no real title available?)
• scientific article; zbMATH DE number 3612796 (Why is no real title available?)
• scientific article; zbMATH DE number 2107175 (Why is no real title available?)
• A radial basis function method for global optimization
• A taxonomy of global optimization methods based on response surfaces
• Bayesian algorithms for one-dimensional global optimization
• Convergence properties of the expected improvement algorithm with fixed mean and covariance functions
• Convergence rates of efficient global optimization algorithms
• Efficient global optimization of expensive black-box functions
• Gaussian processes for machine learning.
• Global optimization

Cited in

(5)

• On the convergence rates of expected improvement methods
• A supermartingale approach to Gaussian process based sequential design of experiments
• Expected improvement for expensive optimization: a review
• Asymptotic Bounds for Smoothness Parameter Estimates in Gaussian Process Interpolation
• Convergence properties of the expected improvement algorithm with fixed mean and covariance functions

Describes a project that uses

Uses Software

• EGO
• SPACE

This page was built for publication: Examples of inconsistency in optimization by expected improvement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2393071)