Sequential stopping rules for the multistart algorithm in global optimisation
- 105 Downloads
In this paper a sequential stopping rule is developed for the Multistart algorithm. A statistical model for the values of the observed local maxima of an objective function is introduced in the framework of Bayesian non-parametric statistics. A suitablea-priori distribution is proposed which is general enough and which leads to computationally manageable expressions for thea-posteriori distribution. Sequential stopping rules of thek-step look-ahead kind are then explicitly derived, and their numerical effectiveness compared.
Key wordsGlobal optimisation Monte Carlo method stopping rules Multistart algorithm Bayes methods
Unable to display preview. Download preview PDF.
- B. Betrò and C. Vercellis, “Bayesian nonparametric inference and Monte Carlo optimization,” I.A.M.I. report 84.20 (Milano, 1984).Google Scholar
- B. Betrò, “The tails of distribution functions from homogeneous processes neutral to the right,” to appear (1984).Google Scholar
- C.G.E. Boender and R. Zieliński, “A sequential Bayesian approach to estimating the dimension of a multinomial distribution,” preprint n. 256, Institute of Mathematics, Polish Academy of Sciences (Warsaw, 1982).Google Scholar
- M.H. De Groot, Optimal Statistical Decisions (McGraw-Hill, New York, 1970).Google Scholar