Efficient space-filling and non-collapsing sequential design strategies for simulation-based modeling

Simulated computer experiments have become a viable cost-effective alternative for controlled real-life experiments. However, the simulation of complex systems with multiple input and output parameters can be a very time-consuming process. Many of these high-fidelity simulators need minutes, hours or even days to perform one simulation. The goal of global surrogate modeling is to create an approximation model that mimics the original simulator, based on a limited number of expensive simulations, but can be evaluated much faster. The set of simulations performed to create this model is called the experimental design. Traditionally, one-shot designs such as the Latin hypercube and factorial design are used, and all simulations are performed before the first model is built. In order to reduce the number of simulations needed to achieve the desired accuracy, sequential design methods can be employed. These methods generate the samples for the experimental design one by one, without knowing the total number of samples in advance. In this paper, the authors perform an extensive study of new and state-of-the-art space-filling sequential design methods. It is shown that the new sequential methods proposed in this paper produce results comparable to the best one-shot experimental designs available right now.

[1]  V. R. Joseph,et al.  ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS , 2008 .

[2]  Rommel G. Regis,et al.  Stochastic radial basis function algorithms for large-scale optimization involving expensive black-box objective and constraint functions , 2011, Comput. Oper. Res..

[3]  Joseph G. Pigeon,et al.  Statistics for Experimenters: Design, Innovation and Discovery , 2006, Technometrics.

[4]  Sonja Kuhnt,et al.  Design and analysis of computer experiments , 2010 .

[5]  Ruichen Jin,et al.  On Sequential Sampling for Global Metamodeling in Engineering Design , 2002, DAC 2002.

[6]  B.G.M. Husslage,et al.  Maximin designs for computer experiments , 2006 .

[7]  Armin Iske,et al.  Hierarchical Nonlinear Approximation for Experimental Design and Statistical Data Fitting , 2007, SIAM J. Sci. Comput..

[8]  Dirk Gorissen,et al.  A Novel Hybrid Sequential Design Strategy for Global Surrogate Modeling of Computer Experiments , 2011, SIAM J. Sci. Comput..

[9]  Peter Z. G. Qian.  Nested Latin hypercube designs , 2009 .

[10]  Robert Lehmensiek,et al.  Adaptive sampling applied to multivariate, multiple output rational interpolation models with application to microwave circuits , 2002 .

[11]  Boxin Tang.  Orthogonal Array-Based Latin Hypercubes , 1993 .

[12]  Arta A. Jamshidi,et al.  Towards a Black Box Algorithm for Nonlinear Function Approximation over High-Dimensional Domains , 2007, SIAM J. Sci. Comput..

[13]  Kenny Q. Ye,et al.  Algorithmic construction of optimal symmetric Latin hypercube designs , 2000 .

[14]  Masashi Sugiyama,et al.  Active Learning in Approximately Linear Regression Based on Conditional Expectation of Generalization Error , 2006, J. Mach. Learn. Res..

[15]  Harald Niederreiter,et al.  Random number generation and Quasi-Monte Carlo methods , 1992, CBMS-NSF regional conference series in applied mathematics.

[16]  Dirk Gorissen,et al.  A novel sequential design strategy for global surrogate modeling , 2009, Proceedings of the 2009 Winter Simulation Conference (WSC).

[17]  Dirk Gorissen,et al.  Adaptive Distributed Metamodeling , 2006, VECPAR.

[18]  Thomas J. Santner,et al.  The Design and Analysis of Computer Experiments , 2003, Springer Series in Statistics.

[19]  Jack Dongarra,et al.  High Performance Computing for Computational Science , 2003 .

[20]  A. Sudjianto,et al.  An Efficient Algorithm for Constructing Optimal Design of Computer Experiments , 2005, DAC 2003.

[21]  Andrea Grosso,et al.  Finding maximin latin hypercube designs by Iterated Local Search heuristics , 2009, Eur. J. Oper. Res..

[22]  Timothy W. Simpson,et al.  Metamodels for Computer-based Engineering Design: Survey and recommendations , 2001, Engineering with Computers.

[23]  Dirk Gorissen,et al.  Space-filling sequential design strategies for adaptive surrogate modelling , 2009, SOCO 2009.

[24]  Fred J. Hickernell,et al.  A generalized discrepancy and quadrature error bound , 1998, Math. Comput..

[25]  Piet Demeester,et al.  A Surrogate Modeling and Adaptive Sampling Toolbox for Computer Based Design , 2010, J. Mach. Learn. Res..

[26]  Wei Chen,et al.  Optimizing Latin hypercube design for sequential sampling of computer experiments , 2009 .

[27]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[28]  Longjun Liu,et al.  Could enough samples be more important than better designs for computer experiments? , 2005, 38th Annual Simulation Symposium.

[29]  Dennis K. J. Lin,et al.  Ch. 4. Uniform experimental designs and their applications in industry , 2003 .

[30]  G. Venter,et al.  An algorithm for fast optimal Latin hypercube design of experiments , 2010 .

[31]  Ben J Hicks,et al.  ASME Design Engineering Technical Conferences and Computers and Information in Engineering Conference , 2009 .

[32]  Inci Batmaz,et al.  Small response surface designs for metamodel estimation , 2003, Eur. J. Oper. Res..

[33]  M. E. Johnson,et al.  Minimax and maximin distance designs , 1990 .

[34]  Dick den Hertog,et al.  Maximin Latin Hypercube Designs in Two Dimensions , 2007, Oper. Res..

[35]  Peter Winker,et al.  Centered L2-discrepancy of random sampling and Latin hypercube design, and construction of uniform designs , 2002, Math. Comput..

[36]  T. J. Mitchell,et al.  Exploratory designs for computational experiments , 1995 .