Abstract

Abstract. This paper presents a taxonomy of existing approaches for using response surfaces for global optimization. Each method is illustrated with a simple numerical example that brings out its advantages and disadvantages. The central theme is that methods that seem quite reasonable often have non-obvious failure modes. Understanding these failure modes is essential for the development of practical algorithms that fulfill the intuitive promise of the response surface approach. Key words: global optimization, response surface, kriging, splines 1.

Citations

168	Global optimization - Törn, Zilinskas - 1989
161	Principals of Econometrics - Theil - 1971
121	Efficient global optimization of expensive black-box functions, Global Optimization 13 - Jones, Schonlau, et al. - 1998
98	A rigorous framework for optimization of expensive functions by surrogates - Booker, Jr, et al. - 1999
98	Direct search methods on parallel machines - Dennis, Torczon - 1991
46	Computer experiments - Koehler, Owen - 1996
33	Design and analysis of computer experiments (with discussion). Stat Sci 4: 409–35 - Sacks, Welch, et al. - 1989
30	A statistical method for global optimization - Cox, John - 1992
28	A radial basis function method for global optimization - Gutmann - 2008
25	Global versus local search in constrained optimization of computer models - Schonlau, Welch, et al. - 1998
15	Application of bayesian approach to numerical methods of global and stochastic optimization - Mockus - 1994
14	A global search method for optimizing nonlinear systems - Stuckman - 1988
12	Optimization with variable-fidelity models applied to wing design - Alexandrov, Lewis, et al.
10	A new method for locating the maximum point of an arbitrary multipeak curve in the presence of noise - Kushner - 1964
9	The global optimisation problem: An introduction - Dixon, Szegö - 1978
8	Metamodeling sampling criteria in a global optimzation framework - Sasena, Papalambros, et al.
6	Bayesian algorithms for one-dimensional global optimization - Locatelli - 1997
5	A computational geometric approach to feasible region division in constrained global optimization - Perttunen - 1991
2	Global R d optimization when probes are expensive: the GROPE algorithm - Elder - 1992
1	Examples of surrogate modeling of computer simulations. Presented at the ISSMO/NASA First Internet Conference on Approximations and Fast Reanalysis in Engineering Optimization - Booker
1	Global Rd optimization when probes are expensive: the GROPE algorithm - Elder - 1992