Abstract
We investigate surrogate-assisted strategies for global derivative-free optimization using the mesh adaptive direct search (MADS) blackbox optimization algorithm. In particular, we build an ensemble of surrogate models to be used within the search step of MADS to perform global exploration, and examine different methods for selecting the best model for a given problem at hand. To do so, we introduce an order-based error tailored to surrogate-based search. We report computational experiments for ten analytical benchmark problems and three engineering design applications. Results demonstrate that different metrics may result in different model choices and that the use of order-based metrics improves performance.
Similar content being viewed by others
Notes
There is an error in the objective function formulation of the SNAKE problem in [65].
References
Abramson, M.A., Audet, C., Dennis Jr., J.E., Le Digabel, S.: OrthoMADS: a deterministic MADS instance with orthogonal directions. SIAM J. Optim. 20(2), 948–966 (2009)
Acar, E., Rais-Rohani, M.: Ensemble of metamodels with optimized weight factors. Struct. Multidiscipl. Optim. 37(3), 279–294 (2009)
Agte, J.S., Sobieszczanski-Sobieski, J., Sandusky, R.R.J.: Supersonic business jet design through bilevel integrated system synthesis. In: Proceedings of the World Aviation Conference, Volume SAE Paper No. 1999-01-5622, San Francisco, CA, 1999. MCB University Press, Bradford
Alexandrov, N.M., Dennis Jr., J.E., Lewis, R.M., Torczon, V.: A trust-region framework for managing the use of approximation models in optimization. Struct. Multidiscipl. Optim. 15(1), 16–23 (1998)
Allen, D.M.: The relationship between variable selection and data agumentation and a method for prediction. Technometrics 16(1), 125–127 (1974)
Audet, C.: A survey on direct search methods for blackbox optimization and their applications. In: Pardalos, P.M., Rassias, T.M. (eds.) Mathematics Without Boundaries: Surveys in Interdisciplinary Research, chapter 2, pp. 31–56. Springer, Berlin (2014)
Audet, C., Béchard, V., Le Digabel, S.: Nonsmooth optimization through mesh adaptive direct search and variable neighborhood search. J. Glob. Optim. 41(2), 299–318 (2008)
Audet, C., Booker, A.J., Dennis Jr., J.E., Frank, P.D., Moore, D.W.: A surrogate-model-based method for constrained optimization. Presented at the 8th AIAA/ISSMO symposium on multidisciplinary analysis and optimization, 2000
Audet, C., Dennis Jr., J.E.: Mesh adaptive direct search algorithms for constrained optimization. SIAM J. Optim. 17(1), 188–217 (2006)
Audet, C., Dennis Jr., J.E.: A progressive barrier for derivative-free nonlinear programming. SIAM J. Optim. 20(1), 445–472 (2009)
Bauer, F., Garabedian, P., Korn, D.: Supercritical Wing Section, vol. III. Springer, Berlin (1977)
Booker, A.J., Dennis Jr., J.E., Frank, P.D., Serafini, D.B., Torczon, V., Trosset, M.W.: A rigorous framework for optimization of expensive functions by surrogates. Struct. Multidiscipl. Optim. 17(1), 1–13 (1999)
Boukouvalaa, F., Floudas, C.A.: ARGONAUT: AlgoRithms for Global Optimization of coNstrAined grey-box compUTational problems. Optim. Lett. 11(5), 895–913 (2017)
Boukouvalaa, F., Hasan, M.M.F., Floudas, C.A.: Global optimization of general constrained grey-box models: new method and its application to constrained PDEs for pressure swing adsorption. J. Glob. Optim. 67(1), 3–42 (2017)
Buhmann, M.D.: Radial Basis Functions: Theory and Implementations. Cambridge Monographs on Applied and Computational Mathematics. Cambridge University Press, Cambridge (2003)
Chen, Y.-C., Wei, C., Yeh, H.-C.: Rainfall network design using kriging and entropy. Hydrol. Process. 22(3), 340–346 (2008)
Chowdhury, S., Mehmani, A., Zhang, J., Messac, A.: Quantifying regional error in surrogates by modeling its relationship with sample density. In: Structures, Structural Dynamics, and Materials and Co-located Conferences. American Institute of Aeronautics and Astronautics (2013)
Colson, B.: Trust-region algorithms for derivative-free optimization and nonlinear bilevel programming. Ph.D. thesis, Département de Mathématique, FUNDP, Namur, Belgium (2003)
Conn, A.R., Le Digabel, S.: Use of quadratic models with mesh-adaptive direct search for constrained black box optimization. Optim. Methods Softw. 28(1), 139–158 (2013)
Conn, A.R., Scheinberg, K., Vicente, L.N.: Introduction to Derivative-Free Optimization. MOS-SIAM Series on Optimization. SIAM, Philadelphia (2009)
Conn, A.R., Toint, P.L.: An algorithm using quadratic interpolation for unconstrained derivative free optimization. In: Di Pillo, G., Gianessi, F. (eds.) Nonlinear Optimization and Applications, pp. 27–47. Plenum Publishing, New York (1996)
Custódio, A.L., Rocha, H., Vicente, L.N.: Incorporating minimum Frobenius norm models in direct search. Comput. Optim. Appl. 46(2), 265–278 (2010)
Dhar, A., Datta, B.: Global optimal design of ground water monitoring network using embedded kriging. Ground Water 47(6), 806–815 (2009)
Eaves, B.C.: On quadratic programming. Manag. Sci. 17(11), 698–711 (1971)
Efron, B.: Estimating the error rate of a prediction rule: improvement on cross-validation. J. Am. Stat. Assoc. 78(382), 316–331 (1983)
Fletcher, R., Gould, N.I.M., Leyffer, S., Toint, P.L., Wächter, A.: On the global convergence of trust-region SQP-filter algorithms for general nonlinear programming. SIAM J. Optim. 13(3), 635–659 (2002)
Fowler, K.R., Reese, J.P., Kees, C.E., Dennis Jr., J.E., Kelley, C.T., Miller, C.T., Audet, C., Booker, A.J., Couture, G., Darwin, R.W., Farthing, M.W., Finkel, D.E., Gablonsky, J.M., Gray, G., Kolda, T.G.: Comparison of derivative-free optimization methods for groundwater supply and hydraulic capture community problems. Adv. Water Resour. 31(5), 743–757 (2008)
Gergonne, J.D.: The application of the method of least squares to the interpolation of sequences. Hist. Math. 1(4), 439–447 (1974)
Goel, T., Haftka, R.T., Shyy, W., Queipo, N.V.: Ensemble of surrogates. Struct. Multidiscipl. Optim. 33(3), 199–216 (2007)
Goel, T., Stander, N.: Comparing three error criteria for selecting radial basis function network topology. Comput. Methods Appl. Mech. Eng. 198(27–29), 2137–2150 (2009)
Goldberg, D.E.: Genetic Algorithms in Search. Optimization and Machine Learning. Addison-Wesley Longman, Boston (1989)
Gramacy, R.B., Gray, G.A., Le Digabel, S., Lee, H.K.H., Ranjan, P., Wells, G., Wild, S.M.: Modeling an augmented lagrangian for blackbox constrained optimization. Technometrics 58(1), 1–11 (2016)
Gramacy, R.B., Le Digabel, S.: The mesh adaptive direct search algorithm with treed Gaussian process surrogates. Pac. J. Optim. 11(3), 419–447 (2015)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer Series in Statistics. Springer, New York (2001)
Hock, W., Schittkowski, K.: Test Examples for Nonlinear Programming Codes. Lecture Notes in Economics and Mathematical Systems, vol. 187. Springer, Berlin (1981)
Jones, D.R., Schonlau, M., Welch, W.J.: Efficient global optimization of expensive black box functions. J. Glob. Optim. 13(4), 455–492 (1998)
Kannan, A., Wild, S.M.: Benefits of deeper analysis in simulation-based groundwater optimization problems. In: Proceedings of the XIX International Conference on Computational Methods in Water Resources (CMWR 2012), June 2012
Kitayama, S., Arakawa, M., Yamazaki, K.: Sequential approximate optimization using radial basis function network for engineering optimization. Optim. Eng. 12(4), 535–557 (2011)
Kodiyalam, S.: Multidisciplinary aerospace systems optimization. Technical Report NASA/CR-2001-211053, Lockheed Martin Space Systems Company, Computational AeroSciences Project, Sunnyvale, CA (2001)
Kroo, I.: Aircraft design: synthesis and analysis; Cruise performance and range. http://adg.stanford.edu/aa241/performance/cruise.html (2005)
Le Digabel, S.: Algorithm 909: NOMAD: nonlinear optimization with the MADS algorithm. ACM Trans. Math. Softw. 37(4), 44:1–44:15 (2011)
Le Thi, H.A., Vaz, A.I.F., Vicente, L.N.: Optimizing radial basis functions by D.C. programming and its use in direct search for global derivative-free optimization. TOP 20(1), 190–214 (2012)
Lim, D., Ong, Y.-S., Jin, Y., Sendhoff, B.: A study on metamodeling techniques, ensembles, and multi-surrogates in evolutionary computation. In: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation, GECCO ’07, pp. 1288–1295. ACM, New York (2007)
Lukšan, L., Vlček, J.: Test problems for nonsmooth unconstrained and linearly constrained optimization. Technical Report V-798, ICS AS CR, 2000
Mack, Y., Goel, T., Shyy, W., Haftka, R.T., Queipo, N.V.: Multiple surrogates for the shape optimization of bluff body-facilitated mixing. In: 43rd AIAA Aerospace Sciences Meeting and Exhibit, Reno, Nevada, 2005. AIAA. Paper AIAA-2005-0333
Mardia, K.V., Kent, J.T., Bibby, J.M.: Multivariate Analysis. Probability and mathematical statistics. Academic Press, New York (1979)
Matott, L.S., Leung, K., Sim, J.: Application of MATLAB and Python optimizers to two case studies involving groundwater flow and contaminant transport modeling. Comput. Geosci. 37(11), 1894–1899 (2011)
Matott, L.S., Rabideau, A.J., Craig, J.R.: Pump-and-treat optimization using analytic element method flow models. Adv. Water Resour. 29(5), 760–775 (2006)
McKay, M.D., Beckman, R.J., Conover, W.J.: A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 21(2), 239–245 (1979)
Mehmani, A., Chowdhury, S., Messac, A.: Predictive quantification of surrogate model fidelity based on modal variations with sample density. Struct. Multidiscipl. Optim. 52(2), 353–373 (2015)
Mladenović, N., Hansen, P.: Variable neighborhood search. Comput. Oper. Res. 24(11), 1097–1100 (1997)
Moré, J.J., Wild, S.M.: Benchmarking derivative-free optimization algorithms. SIAM J. Optim. 20(1), 172–191 (2009)
Müller, J., Piché, R.: Mixture surrogate models based on Dempster-Shafer theory for global optimization problems. J. Glob. Optim. 51(1), 79–104 (2011)
Müller, J., Shoemaker, C.A.: Influence of ensemble surrogate models and sampling strategy on the solution quality of algorithms for computationally expensive black-box global optimization problems. J. Glob. Optim. 60(2), 123–144 (2014)
Orr, M.J.L.: Introduction to radial basis function networks. Technical report, Center for Cognitive Science, University of Edinburgh (1996)
Peremezhney, N., Hines, E., Lapkin, A., Connaughton, C.: Combining gaussian processes, mutual information and a genetic algorithm for multi-target optimization of expensive-to-evaluate functions. Eng. Optim. 46(11), 1593–1607 (2014)
Queipo, N.V., Haftka, R.T., Shyy, W., Goel, T., Vaidyanathan, R., Tucher, P.K.: Surrogate-based analysis and optimization. Prog. Aerosp. Sci. 41(1), 1–28 (2005)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2006)
Regis, R.G.: Stochastic radial basis function algorithms for large-scale optimization involving expensive black-box objective and constraint functions. Comput. Oper. Res. 38(5), 837–853 (2011)
Regis, R.G.: Constrained optimization by radial basis function interpolation for high-dimensional expensive black-box problems with infeasible initial points. Eng. Optim. 46(2), 218–243 (2014)
Shi, R., Liu, L., Long, T., Liu, J.: An efficient ensemble of radial basis functions method based on quadratic programming. Eng. Optim. 48(7), 1202–1225 (2016)
Stigler, S.M.: Gergonne’s 1815 paper on the design and analysis of polynomial regression experiments. Hist. Math. 1(4), 431–439 (1974)
Stone, M.: An asymptotic equivalence of choice of model by cross-validation and Akaike’s criterion. J. R. Stat. Soc. Ser. B (Methodol.) 39(1), 44–47 (1977)
Taddy, M.A., Gramacy, R.B., Polson, N.G.: Dynamic trees for learning and design. J. Am. Stat. Assoc. 106(493), 109–123 (2011)
Talgorn, B., Le Digabel, S., Kokkolaras, M.: Statistical surrogate formulations for simulation-based design optimization. J. Mech. Des. 137(2), 021405-1–021405-18 (2015)
Tarpey, T.: A note on the prediction sum of squares statistic for restricted least squares. Am. Stat. 54(2), 116–118 (2000)
Tenne, Y.: An adaptive-topology ensemble algorithm for engineering optimization problems. Optim. Eng. 16(2), 303–334 (2014)
Tosserams, S., Etman, L.F.P., Rooda, J.E.: A classification of methods for distributed system optimization based on formulation structure. Struct. Multidiscipl. Optim. 39(5), 503–517 (2009)
Tournemenne, R., Petiot, J.-F., Talgorn, B., Kokkolaras, M., Gilbert, J.: Brass instruments design using physics-based sound simulation models and surrogate-assisted derivative-free optimization. J. Mech. Des. 139(4), 041401-01–04140-19 (2017)
Tribes, C., Dubé, J.-F., Trépanier, J.-Y.: Decomposition of multidisciplinary optimization problems: formulations and application to a simplified wing design. Eng. Optim. 37(8), 775–796 (2005)
Vaz, A.I.F., Vicente, L.N.: A particle swarm pattern search method for bound constrained global optimization. J. Glob. Optim. 39(2), 197–219 (2007)
Viana, F.A.C., Haftka, R.T., Valder Jr., S., Butkewitsch, S., Leal, M.F.: Ensemble of Surrogates: a Framework based on Minimization of the Mean Integrated Square Error. In: 49th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials, Schaumburg, IL (2008)
Viana, F.A.C., Haftka, R.T., Watson, L.T.: Efficient global optimization algorithm assisted by multiple surrogate techniques. J. Glob. Optim. 56(2), 669–689 (2013)
Watson, G.S.: Smoothing and interpolation by kriging and with splines. Math. Geol. 16, 601–615 (1984)
Wild, S.M., Regis, R.G., Shoemaker, C.A.: ORBIT: optimization by radial basis function interpolation in trust-regions. SIAM J. Sci. Comput. 30(6), 3197–3219 (2008)
Acknowledgements
This work has been supported partially by FRQNT Grant 2015-PR-182098; B. Talgorn and M. Kokkolaras are grateful for the partial support of NSERC/Hydro-Québec Grant EGP2 498903-16; such support does not constitute an endorsement by the sponsors of the opinions expressed in this article. The authors would like to thank Robin Tournemenne (École Centrale de Nantes) for his insightful questions and comments that contributed significantly to improve the search algorithm used in this work. The authors would also like to express their gratitude to Stéphane Alarie (IREQ) for his support, which made this work possible.
Author information
Authors and Affiliations
Corresponding author
Appendices
Greedy selection algorithm
This greedy algorithm is used in Sect. 2.2 to filter the set of projection candidates and in Sect. 3.1.2 to select a subset of the training points around which the radial basis functions will be centered. For the projection step, the inputs of Algorithm 2 are:
For the selection of the RBF kernels, the inputs of Algorithm 2 are:
In both cases, the goal of this algorithm is to select a set \(S_{out}\) of \(p_{out}\) points from the set \(S_{in}\in {\mathbb {R}}^n\). The set \(S_{out}\) must be spread as widely as possible in \({\mathbb {R}}^n\) while favoring points that are close to a target \(\mathbf {x}_{0}\). Since these two goals can be conflicting, a trade-off parameter \(\lambda \) is introduced. When many points that are close to \(\mathbf {x}_{0}\) have been selected, it is possible that the goal of selecting even more points close to \(\mathbf {x}_{0}\) will lead to selecting a point that is already selected. In that case, the trade-off coefficient \(\lambda \) is decreased.
Description of the analytical problems
1.1 MAD6 [44]
The original formulation uses seven variables, but two linear equality constraints allow to express the problem with five variables as follows:
where, for \(1\le i \le 163\),
and
Best value achieved in this work: \(f=0.101831\).
1.2 CRESCENT [1, 10]
Best value achieved in this work: \(f = -9\).
1.3 SNAKE [10, 19]
Best value achieved in this work: \(f=0.08098094\).Footnote 1
1.4 HS24 [35]
Best value achieved in this work: \(f=-1\).
1.5 HS36 [35]
Best value achieved in this work: \(f=-3300\).
1.6 HS37 [35]
Best value achieved in this work: \(f=-3456\).
1.7 HS73 [35]
In the original problem, the value of \(x_4\) is computed directly by eliminating one linear equality constraint (\(x_4=1-x_1-x_2-x_3\)). Constraint \(c_3\) is added to handle the bound \(x_4 \ge 0\).
Best value achieved in this work: \(f=29.8944\).
1.8 HS101, 102 and 103 [35]
The value of the parameter a varies between the three problems:
The starting point is \( \mathbf {x}_0= [ 6 \; 6 \; 6 \; 6 \; 6 \; 6 \; 6 ]^\top \) with the value \(f(\mathbf {x}_0)=+\infty \) (\(\mathbf {x}_0\) is infeasible) and the best know solutions are:
with
The best values achieved in this work are 2480.94, 1950.26, and 3367.69, for HS101, HS102, and HS103, respectively.
Data profiles
For a given tolerance \(\tau \le 1\), the ratio of solved problems for solver s after i groups of \(n+1\) evaluations is defined as:
where \(\mathbb {1}\) is the indicator function. Note that if \(\tau =1\), a problem is considered solved if a feasible solution has been found. For a given value of \(\tau \), the data profile is the curve corresponding to the ratio of solved problems after i groups of \(n+1\) evaluations [52]. For the set of analytical problems and for the two sets of MDO runs (simplified wing and aircraft range), we show the data profiles for \(\tau \in \{10^{-3},10^{-5},10^{-7}\}\) (see Figs. 9, 10, 11). For the Lockwood problem runs, to which is allocated a much smaller budget of evaluations, we show the data profiles for \(\tau \in \{10^{-1},10^{-2},10^{-3}\}\) (see Fig. 12). Note that for the medium discrepancy curve, the lower the curve value, the better the performance. However, for the data profiles, the higher the better.
Rights and permissions
About this article
Cite this article
Audet, C., Kokkolaras, M., Le Digabel, S. et al. Order-based error for managing ensembles of surrogates in mesh adaptive direct search. J Glob Optim 70, 645–675 (2018). https://doi.org/10.1007/s10898-017-0574-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-017-0574-1