Humphrey, D.G., J.R. Wilson. 1998. A Revised Simplex Search procedure for Stochastic Simulation Response-Surface Optimization. D.J. Medeiros, E.F. Watson, J.S. Carson, M.S. Manivannan, eds. Proceedings of the 1998 Winter Simulation Conference. IEEE Press, Piscataway, NJ. 751-759. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Adaptive Extensions of the Nelder and Mead Simplex Method.. - Neddermeijer, al. (2000) (Correct)
....They consider the average of a number of replicated observations to evaluate the stochastic objective function. The number of replications used in an iteration step is determined dynamically by considering a statistical test on the di erences of the function values in the current simplex. Humphrey and Wilson (1998) designed a three phase application of the Nelder and Mead Simplex Method that is based on restart. The size of the initial simplex and the way the simplex is shrunk during an optimization run is changed in each phase of their algorithm. The incentive for starting a new phase is based on the size ....
....shrink step rather than 50 ( 0#5) They found that the modi ed algorithm, when applied to stochastic objective functions, leads to improvements in the expected value of the objective function at termination at the cost of more function evaluations. Other studies (Tomick, Arnold, and Barton 1995; Humphrey and Wilson, 1998; Neddermeijer et al. 1999) also found this modi cation to perform signi cantly better for stochastic functions. We include this second modi cation in the benchmark algorithm, since we are especially interested in a simplex algorithm that further improves the performance on stochastic problems ....
Humphrey, D.G., J.R. Wilson. 1998. A Revised Simplex Search procedure for Stochastic Simulation Response-Surface Optimization. D.J. Medeiros, E.F. Watson, J.S. Carson, M.S. Manivannan, eds. Proceedings of the 1998 Winter Simulation Conference. IEEE Press, Piscataway, NJ. 751-759.
A Revised Simplex Search Procedure For Stochastic Simulation .. - Humphrey, Wilson (2000) (1 citation) Self-citation (Humphrey) (Correct)
....The surprising conclusion was that induced positive correlation yields little or no improvement in the rate of convergence to the optimum for the NM procedure. Space limitations preclude further discussion of this phenomenon in the present paper. See Humphrey and Wilson [10] and Humphrey [11] for a detailed analysis of the e ect of induced correlation on the performance of procedure NM. 2 Review of Procedures NM and RS9 In this section we discuss the characteristics of the procedure by Nelder and Mead as well as the variant of this procedure proposed by Barton and Ivey. 2.1 ....
Humphrey, D., \A Revised Simplex Search Procedure for Stochastic Simulation Response Surface Optimization," Ph.D. Dissertation, Department of Industrial Engineering, North Carolina State University, Raleigh, North Carolina.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC