Analysis of multi-objective Kriging-based methods for constrained global optimization
详细信息 查看全文
- 作者：Cédric Durantin ; Julien Marzat…
- 关键词：Black ; box functions ; Constrained global optimization ; Kriging ; Multi ; objective optimization
- 刊名：Computational Optimization and Applications
- 出版年：2016
- 出版时间：April 2016
- 年：2016
- 卷：63
- 期：3
- 页码：903-926
- 全文大小：2,722 KB
- 参考文献：1.Krige, D.G.: A statistical approach to some basic mine valuation problems on the witwatersrand. J. Chem. Metall. Min. Soc. S. Afr. 52(6), 119–139 (1951)
2.Schonlau, M., Welch, W.J.: Global optimization with nonparametric function fitting. In: Proceedings of the ASA, Section on Physical and Engineering Sciences, pp. 183–186. (1996)
3.Jones, D.R., Schonlau, M.J., Welch, W.J.: Efficient global optimization of expensive black-box functions. J. Glob. Optim. 13(4), 455–492 (1998)CrossRef MathSciNet MATH
4.Kushner, H.J.: A new method of locating the maximum point of an arbitrary multipeak curve in the presence of noise. J. Fluids Eng. 86(1), 97–106 (1964)MathSciNet
5.Kleijnen, J.P.C.: Kriging metamodeling in simulation: a review. Eur. J. Oper. Res. 192(3), 707–716 (2009)CrossRef MathSciNet MATH
6.Picheny, V.: A stepwise uncertainty reduction approach to constrained global optimization. In: Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, Reykjavik, Iceland, pp. 787–795. (2014)
7.Basudhar, A., Dribusch, C., Lacaze, S., Missoum, S.: Constrained efficient global optimization with support vector machines. Struct. Multidiscip. Optim. 46(2), 201–221 (2012)CrossRef MATH
8.Parr, J.M., Keane, A.J., Forrester, A.I.J., Holden, C.M.E.: Infill sampling criteria for surrogate-based optimization with constraint handling. Eng. Optim. 44(10), 1147–1166 (2012)CrossRef
9.Fletcher, R., Leyffer, S.: Nonlinear programming without a penalty function. Math. Program. 91(2), 239–269 (2002)CrossRef MathSciNet MATH
10.Audet, C., Dennis Jr, J.E.: A pattern search filter method for nonlinear programming without derivatives. SIAM J. Optim. 14(4), 980–1010 (2004)CrossRef MathSciNet MATH
11.Audet, C., Dennis Jr, J.E.: A progressive barrier for derivative-free nonlinear programming. SIAM J. Optim. 20(1), 445–472 (2009)CrossRef MathSciNet MATH
12.Le Digabel, S.: Algorithm 909: NOMAD: nonlinear optimization with the MADS algorithm. ACM Trans. Math. Softw. 37(4), 44 (2011)CrossRef
13.Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. Springer, New York (2006)MATH
14.Vazquez, E.: Modélisation comportementale de systèmes non-linéaires multivariables par méthodes à noyaux et applications. PhD thesis, Université Paris Sud-Paris XI. (2005)
15.Santner, T.J., Williams, B.J., Notz, W.: The Design and Analysis of Computer Experiments. Springer, Berlin (2003)CrossRef MATH
16.Hansen, N., Kern, S.: Evaluating the CMA evolution strategy on multimodal test functions. In: Parallel Problem Solving from Nature-PPSN VIII, pp. 282–291. Springer, New York (2004)
17.Jones, D.R.: A taxonomy of global optimization methods based on response surfaces. J. Glob. Optim. 21(4), 345–383 (2001)CrossRef MATH
18.Forrester, A.I.J., Sobester, A., Keane, A.J.: Engineering Design via Surrogate Modelling: A Practical Guide. Wiley, Chichester (2008)CrossRef
19.Sasena, M.J.: Flexibility and efficiency enhancements for constrained global design optimization with Kriging approximations. PhD Thesis, University of Michigan, Ann Arbor. (2002)
20.Jones, D.R., Perttunen, C.D., Stuckman, B.E.: Lipschitzian optimization without the Lipschitz constant. J. Optim. Theory Appl. 79(1), 157–181 (1993)CrossRef MathSciNet MATH
21.Vazquez, E., Bect, J.: Convergence properties of the expected improvement algorithm with fixed mean and covariance functions. J. Stat. Plan. Inference 140(11), 3088–3095 (2010)CrossRef MathSciNet MATH
22.Sasena, M.J., Papalambros, P.Y., Goovaerts, P.: The use of surrogate modeling algorithms to exploit disparities in function computation time within simulation-based optimization. Constraints 2, 5 (2001)
23.Audet, C., Dennis Jr, J.E.: Mesh adaptive direct search algorithms for constrained optimization. SIAM J. Optim. 17(1), 188–217 (2006)CrossRef MathSciNet MATH
24.Hansen, N.: The CMA evolution strategy: a comparing review. In Towards a New Evolutionary Computation, pp. 75–102. Springer, New York (2006)
25.Audet,C., Booker, A.J., Dennis Jr., J.E., Frank, P.D., Moore, D.W.: A surrogate-model-based method for constrained optimization. In: Proceedings of the 8th AIAA/NASA/USAF/ISSMO Symposium on Multidisciplinary Analysis and Optimization, Long Beach, CA, USA. Paper No. AIAA-2000-4891 (2000)
26.Parr, J.M., Forrester, A.I.J., Keane, A.J., Holden, C.M.E.: Enhancing infill sampling criteria for surrogate-based constrained optimization. J. Comput. Methods Sci. Eng. 12(1), 25–45 (2012)MathSciNet MATH
27.Waldock, A., Corne, D.: Multiple objective optimisation applied to route planning. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, Dublin, pp. 1827–1834. ACM (2011)
28.Deb, K.: Multi-objective Optimization Using Evolutionary Algorithms. Wiley, Chichester (2001)MATH
29.Audet, C., Savard, G., Zghal, W.: A mesh adaptive direct search algorithm for multiobjective optimization. Eur. J. Oper. Res. 204(3), 545–556 (2010)CrossRef MathSciNet MATH - 作者单位：Cédric Durantin (1)
Julien Marzat (2)
Mathieu Balesdent (2)
1. University Grenoble Alpes, CEA, LETI, MINATEC Campus, 38054, Grenoble, France
2. ONERA - The French Aerospace Lab, 91123, Palaiseau, France - 刊物类别：Mathematics and Statistics
- 刊物主题：Mathematics
Optimization
Operations Research and Mathematical Programming
Operation Research and Decision Theory
Statistics
Convex and Discrete Geometry - 出版者：Springer Netherlands
- ISSN：1573-2894
文摘
Metamodeling, i.e., building surrogate models to expensive black-box functions, is an interesting way to reduce the computational burden for optimization purpose. Kriging is a popular metamodel based on Gaussian process theory, whose statistical properties have been exploited to build efficient global optimization algorithms. Single and multi-objective extensions have been proposed to deal with constrained optimization when the constraints are also evaluated numerically. This paper first compares these methods on a representative analytical benchmark. A new multi-objective approach is then proposed to also take into account the prediction accuracy of the constraints. A numerical evaluation is provided on the same analytical benchmark and a realistic aerospace case study.