Journal of Global Optimization

, Volume 10, Issue 1, pp 57–76 | Cite as

Bayesian Algorithms for One-Dimensional Global Optimization

  • M. Locatelli
Article

Abstract

In this paper Bayesian analysis and Wiener process are used in orderto build an algorithm to solve the problem of globaloptimization.The paper is divided in two main parts.In the first part an already known algorithm is considered: a new (Bayesian)stopping ruleis added to it and some results are given, such asan upper bound for the number of iterations under the new stopping rule.In the second part a new algorithm is introduced in which the Bayesianapproach is exploited not onlyin the choice of the Wiener model but also in the estimationof the parameter σ2 of the Wiener process, whose value appears to bequite crucial.Some results about this algorithm are also given.

Bayesian analysis Wiener process stopping rule. 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    B. Betró, F. Schoen (1992), Optimal and sub-optimal stopping rules for the Multistart algorithm in global optimization, Mathematical Programming 57, 445–458.Google Scholar
  2. 2.
    J.M. Calvin (1991), Consistency of a myopic bayesian algorithm for global optimization, Technical Report,Georgia Institute of Technology.Google Scholar
  3. 3.
    M.H. DeGroot (1970), Optimal Statistical Decisions,McGraw-Hill, New York.Google Scholar
  4. 4.
    A. O’Hagan (1978), Curve fitting and optimal design for prediction, Journal of Royal Statistical Society B 40, 1–42.Google Scholar
  5. 5.
    A. O’Hagan (1991), Some bayesian numerical analysis, Technical Report, University of Nottingham.Google Scholar
  6. 6.
    H. Kushner (1962), A versatile stochastic model of a function of unknown and time varying form, Journal of Math.Anal.Appl. 5, 150–167.Google Scholar
  7. 7.
    M. Locatelli (1992), Algoritmi bayesiani per l’ottimizzazione globale, unpublished laurea thesis.Google Scholar
  8. 8.
    M. Locatelli, F. Schoen (1993), An adaptive stochastic global optimization algorithm for onedimensional functions, Proceedings of APMOD93,BudapestGoogle Scholar
  9. 9.
    J. Mockus (1988), Bayesian Approach to Global Optimization,Kluwer Academic Publishers, Dordrecht.Google Scholar
  10. 10.
    A.M. Mood, F.A. Graybill, D.C. Boes (1974), Introduction to the Theory of Statistics,McGraw-Hill, New York.Google Scholar
  11. 11.
    D. Revuz, M. Yor (1991), Continuous Martingales and Brownian Motion, Springer Verlag, Berlin.Google Scholar
  12. 12.
    E. Senkiene, A. Zilinskas (1978), On estimation of a parameter of Wiener process, Lithuanian Mathematical Journal 3, 59–62.Google Scholar
  13. 13.
    R.G. Strongin (1992), Algorithms for multi-extremal mathematical programming problems employing the set of joint space-filling curves, Journal of Global Optimization 2, 357–378.Google Scholar
  14. 14.
    A. Törn, A. Zilinskas (1987), Global Optimization,Springer Verlag, Berlin. Google Scholar
  15. 15.
    A.A. Zhigljavsky (1991), Theory of Global Random Search,Kluwer Academic Publishers, Dordrecht.Google Scholar
  16. 16.
    A. Zilinskas (1975), One-step Bayesianmethod of the search for extremum of an one-dimensional function, Cybernetics 1, 139–144.Google Scholar

Copyright information

© Kluwer Academic Publishers 1997

Authors and Affiliations

  • M. Locatelli
    • 1
  1. 1.Dipartimento di Scienze dell‘InformazioneUniversità degli studi di MilanoMilanoItaly

Personalised recommendations