EUVIMEDEUVIMED entdecken
Crossref

Data-Efficient Design Exploration through Surrogate-Assisted Illumination

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret

Evolutionary Computation · 2018-09 · 26 (3) · 381-410

DOI: 10.1162/evco_a_00231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Evolutionary Computation, 2018-09. Verfasst von Adam Gaier und 2 weiteren Autor:innen. Beteiligte Einrichtung: Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France Bonn-Rhein-Sieg University of Applied Sciences, Sankt Augustin, 53757, Germany adam…. Hauptthemen laut MEDLINE: Algorithms, Bayes Theorem, Computer Simulation, Data Interpretation, Statistical. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 42 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Design optimization techniques are often used at the beginning of the design process to explore the space of possible designs. In these domains illumination algorithms, such as MAP-Elites, are promising alternatives to classic optimization algorithms because they produce diverse, high-quality solutions in a single run, instead of only a single near-optimal solution. Unfortunately, these algorithms currently require a large number of function evaluations, limiting their applicability. In this article, we introduce a new illumination algorithm, Surrogate-Assisted Illumination (SAIL), that leverages surrogate modeling techniques to create a map of the design space according to user-defined features while minimizing the number of fitness evaluations. On a two-dimensional airfoil optimization problem, SAIL produces hundreds of diverse but high-performing designs with several orders of magnitude fewer evaluations than MAP-Elites or CMA-ES. We demonstrate that SAIL is also capable of producing maps of high-performing designs in realistic three-dimensional aerodynamic tasks with an accurate flow simulation. Data-efficient design exploration with SAIL can help designers understand what is possible, beyond what is optimal, by considering more than pure objective-based optimization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsBayes TheoremComputer SimulationData Interpretation, StatisticalQuality ControlBiomechanical PhenomenaLightingSoftware

Stichwörter der Autor:innen

MAP-Elitescomputer automated design.quality-diversitysurrogate modeling

Autor:innen und Institutionen

  • Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France Bonn-Rhein-Sieg University of Applied Sciences, Sankt Augustin, 53757, Germany adam.gaier@h-brs.de.
  • Bonn-Rhein-Sieg University of Applied Sciences, Sankt Augustin, 53757, Germany alexander.asteroth@h-brs.de.
  • Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France jean-baptiste.mouret@inria.fr.

Zitieren

APA

Gaier, A., Asteroth, A., & Mouret, J. B. (2018). Data-Efficient Design Exploration through Surrogate-Assisted Illumination. Evolutionary Computation, 26(3), 381-410. https://doi.org/10.1162/evco_a_00231

Vancouver

Gaier A, Asteroth A, Mouret JB. Data-Efficient Design Exploration through Surrogate-Assisted Illumination. Evolutionary Computation. 2018;26(3):381-410. doi:10.1162/evco_a_00231

BibTeX
@article{Gaier2018,
  author = {Gaier, Adam and Asteroth, Alexander and Mouret, Jean-Baptiste},
  title = {Data-Efficient Design Exploration through Surrogate-Assisted Illumination},
  journal = {Evolutionary Computation},
  year = {2018},
  volume = {26},
  number = {3},
  pages = {381--410},
  doi = {10.1162/evco_a_00231}
}
Kostenlos starten →