Examples of inconsistency in optimization by expected improvement

DOI10.1007/S10898-012-9936-XzbMATH Open1291.90156arXiv1109.1320OpenAlexW2105215483MaRDI QIDQ2393071FDOQ2393071

Authors: Dmitry Yarotsky 

Publication date: 7 August 2013

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

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.

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

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

zbMATH Keywords

expected improvementBayesian optimizationanalytic kernelGaussian covariance function

Mathematics Subject Classification ID

Stochastic programming (90C15)

Cites Work

• Efficient global optimization of expensive black-box functions
• Gaussian processes for machine learning.
• A taxonomy of global optimization methods based on response surfaces
• Title not available (Why is that?)
• Convergence properties of the expected improvement algorithm with fixed mean and covariance functions
• Title not available (Why is that?)
• A radial basis function method for global optimization
• Convergence rates of efficient global optimization algorithms
• Title not available (Why is that?)
• Title not available (Why is that?)
• Global optimization
• Bayesian algorithms for one-dimensional 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

Uses Software

• SPACE
• EGO

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)