Advanced search
1 file | 1.28 MB

Evolutionary model type selection for global surrogate modeling

Dirk Gorissen (UGent) , Tom Dhaene (UGent) and Filip De Turck (UGent)
Author
Organization
Abstract
Due to the scale and computational complexity of currently used simulation codes, global surrogate (metamodels) models have become indispensable tools for exploring and understanding the design space. Due to their compact formulation they are cheap to evaluate and thus readily facilitate visualization, design space exploration, rapid prototyping, and sensitivity analysis. They can also be used as accurate building blocks in design packages or larger simulation environments. Consequently, there is great interest in techniques that facilitate the construction of such approximation models while minimizing the computational cost and maximizing model accuracy. Many surrogate model types exist ( Support Vector Machines, Kriging, Neural Networks, etc.) but no type is optimal in all circumstances. Nor is there any hard theory available that can help make this choice. In this paper we present an automatic approach to the model type selection problem. We describe an adaptive global surrogate modeling environment with adaptive sampling, driven by speciated evolution. Different model types are evolved cooperatively using a Genetic Algorithm ( heterogeneous evolution) and compete to approximate the iteratively selected data. In this way the optimal model type and complexity for a given data set or simulation code can be dynamically determined. Its utility and performance is demonstrated on a number of problems where it outperforms traditional sequential execution of each model type.
Keywords
ENGINEERING DESIGN, INFINITE POPULATION-SIZE, THEORETICAL-ANALYSIS, METAMODELING TECHNIQUES, CONTINUOUS SPACE, model type selection, genetic algorithms, global surrogate modeling, function approximation, active learning, adaptive sampling, ALGORITHMS, OPTIMIZATION, NEURAL-NETWORKS, APPROXIMATION, SIMULATION

Downloads

  • Gorissen 2009 JMLR 10 2039.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.28 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Gorissen, Dirk, Tom Dhaene, and Filip De Turck. 2009. “Evolutionary Model Type Selection for Global Surrogate Modeling.” Journal of Machine Learning Research 10: 2039–2078.
APA
Gorissen, D., Dhaene, T., & De Turck, F. (2009). Evolutionary model type selection for global surrogate modeling. JOURNAL OF MACHINE LEARNING RESEARCH, 10, 2039–2078.
Vancouver
1.
Gorissen D, Dhaene T, De Turck F. Evolutionary model type selection for global surrogate modeling. JOURNAL OF MACHINE LEARNING RESEARCH. 2009;10:2039–78.
MLA
Gorissen, Dirk, Tom Dhaene, and Filip De Turck. “Evolutionary Model Type Selection for Global Surrogate Modeling.” JOURNAL OF MACHINE LEARNING RESEARCH 10 (2009): 2039–2078. Print.
@article{858680,
  abstract     = {Due to the scale and computational complexity of currently used simulation codes, global surrogate (metamodels) models have become indispensable tools for exploring and understanding the design space. Due to their compact formulation they are cheap to evaluate and thus readily facilitate visualization, design space exploration, rapid prototyping, and sensitivity analysis. They can also be used as accurate building blocks in design packages or larger simulation environments. Consequently, there is great interest in techniques that facilitate the construction of such approximation models while minimizing the computational cost and maximizing model accuracy. Many surrogate model types exist ( Support Vector Machines, Kriging, Neural Networks, etc.) but no type is optimal in all circumstances. Nor is there any hard theory available that can help make this choice. In this paper we present an automatic approach to the model type selection problem. We describe an adaptive global surrogate modeling environment with adaptive sampling, driven by speciated evolution. Different model types are evolved cooperatively using a Genetic Algorithm ( heterogeneous evolution) and compete to approximate the iteratively selected data. In this way the optimal model type and complexity for a given data set or simulation code can be dynamically determined. Its utility and performance is demonstrated on a number of problems where it outperforms traditional sequential execution of each model type.},
  author       = {Gorissen, Dirk and Dhaene, Tom and De Turck, Filip},
  issn         = {1532-4435},
  journal      = {JOURNAL OF MACHINE LEARNING RESEARCH},
  keywords     = {ENGINEERING DESIGN,INFINITE POPULATION-SIZE,THEORETICAL-ANALYSIS,METAMODELING TECHNIQUES,CONTINUOUS SPACE,model type selection,genetic algorithms,global surrogate modeling,function approximation,active learning,adaptive sampling,ALGORITHMS,OPTIMIZATION,NEURAL-NETWORKS,APPROXIMATION,SIMULATION},
  language     = {eng},
  pages        = {2039--2078},
  title        = {Evolutionary model type selection for global surrogate modeling},
  url          = {http://jmlr.csail.mit.edu/papers/v10/gorissen09a.html},
  volume       = {10},
  year         = {2009},
}

Web of Science
Times cited: