论文信息 - Sample size selection for improved Nelder-Mead performance

Sample size selection for improved Nelder-Mead performance

The Nelder-Mead (1965) simplex algorithm has been used for sequential optimization of simulation response functions. The rescaling operations of this algorithm can lead to inappropriate termination at non-optimal points. We have used the probabilistic characterization of this behaviour to develop special rules for determining the number of replications to take for each experimental design point. Computational experiments indicate that the quality of the solution is often improved.

Russell R. Barton | Steven F. Arnold | John J. Tomick

[1] John A. Nelder,et al. A Simplex Method for Function Minimization , 1965, Comput. J..

[2] J. Kiefer,et al. Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[3] Russell R. Barton,et al. On convergence of the nelder-mead simplex algorithm for unconstrained stochastic optimization , 1995 .

[4] Michael C. Fu,et al. A tutorial review of techniques for simulation optimization , 1994, Proceedings of Winter Simulation Conference.

[5] Farhad Azadivar,et al. A tutorial on simulation optimization , 1992, WSC '92.

[6] James C. Spall,et al. Developments in stochastic optimization algorithms with gradient approximations based on function measurements , 1994, Proceedings of Winter Simulation Conference.

[7] J. S. Ivey,et al. Nelder-Mead simplex modifications for simulation optimization , 1996 .

[8] Jack J. Dongarra,et al. Distribution of mathematical software via electronic mail , 1985, SGNM.

[9] J. W. Akitt. Function Minimisation Using the Nelder and Mead Simplex Method with Limited Arithmetic Precision: The Self Regenerative Simplex , 1977, Comput. J..

[10] DEVELOPMENTS IN STOCHASTIC OPTIMIZATION ALGORITHMS WITH GRADIENT APPROXIMATIONS BASED ON FUNCTION MEASUREMENTS , 1994 .

[11] Jorge J. Moré,et al. Testing Unconstrained Optimization Software , 1981, TOMS.