Advanced search
2 files | 8.26 MB Add to list

A robust multi-objective Bayesian optimization framework considering input uncertainty

Jixiang Qing (UGent) , Ivo Couckuyt (UGent) and Tom Dhaene (UGent)
(2023) JOURNAL OF GLOBAL OPTIMIZATION. 86(3). p.693-711
Author
Organization
Project
Abstract
Bayesian optimization is a popular tool for optimizing time-consuming objective functions with a limited number of function evaluations. In real-life applications like engineering design, the designer often wants to take multiple objectives as well as input uncertainty into account to find a set of robust solutions. While this is an active topic in single-objective Bayesian optimization, it is less investigated in the multi-objective case. We introduce a novel Bayesian optimization framework to perform multi-objective optimization considering input uncertainty. We propose a robust Gaussian Process model to infer the Bayes risk criterion to quantify robustness, and we develop a two-stage Bayesian optimization process to search for a robust Pareto frontier, i.e., solutions that have good average performance under input uncertainty. The complete framework supports various distributions of the input uncertainty and takes full advantage of parallel computing. We demonstrate the effectiveness of the framework through numerical benchmarks.
Keywords
Efficient global optimization, Robust optimization, Bayesian, optimization, Gaussian process

Downloads

  • 8216 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 5.61 MB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.65 MB

Citation

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

MLA
Qing, Jixiang, et al. “A Robust Multi-Objective Bayesian Optimization Framework Considering Input Uncertainty.” JOURNAL OF GLOBAL OPTIMIZATION, vol. 86, no. 3, 2023, pp. 693–711, doi:10.1007/s10898-022-01262-9.
APA
Qing, J., Couckuyt, I., & Dhaene, T. (2023). A robust multi-objective Bayesian optimization framework considering input uncertainty. JOURNAL OF GLOBAL OPTIMIZATION, 86(3), 693–711. https://doi.org/10.1007/s10898-022-01262-9
Chicago author-date
Qing, Jixiang, Ivo Couckuyt, and Tom Dhaene. 2023. “A Robust Multi-Objective Bayesian Optimization Framework Considering Input Uncertainty.” JOURNAL OF GLOBAL OPTIMIZATION 86 (3): 693–711. https://doi.org/10.1007/s10898-022-01262-9.
Chicago author-date (all authors)
Qing, Jixiang, Ivo Couckuyt, and Tom Dhaene. 2023. “A Robust Multi-Objective Bayesian Optimization Framework Considering Input Uncertainty.” JOURNAL OF GLOBAL OPTIMIZATION 86 (3): 693–711. doi:10.1007/s10898-022-01262-9.
Vancouver
1.
Qing J, Couckuyt I, Dhaene T. A robust multi-objective Bayesian optimization framework considering input uncertainty. JOURNAL OF GLOBAL OPTIMIZATION. 2023;86(3):693–711.
IEEE
[1]
J. Qing, I. Couckuyt, and T. Dhaene, “A robust multi-objective Bayesian optimization framework considering input uncertainty,” JOURNAL OF GLOBAL OPTIMIZATION, vol. 86, no. 3, pp. 693–711, 2023.
@article{01GMZB29V2W3B3THVE1F67C5N8,
  abstract     = {{Bayesian optimization is a popular tool for optimizing time-consuming objective functions with a limited number of function evaluations. In real-life applications like engineering design, the designer often wants to take multiple objectives as well as input uncertainty into account to find a set of robust solutions. While this is an active topic in single-objective Bayesian optimization, it is less investigated in the multi-objective case. We introduce a novel Bayesian optimization framework to perform multi-objective optimization considering input uncertainty. We propose a robust Gaussian Process model to infer the Bayes risk criterion to quantify robustness, and we develop a two-stage Bayesian optimization process to search for a robust Pareto frontier, i.e., solutions that have good average performance under input uncertainty. The complete framework supports various distributions of the input uncertainty and takes full advantage of parallel computing. We demonstrate the effectiveness of the framework through numerical benchmarks.}},
  author       = {{Qing, Jixiang and Couckuyt, Ivo and Dhaene, Tom}},
  issn         = {{0925-5001}},
  journal      = {{JOURNAL OF GLOBAL OPTIMIZATION}},
  keywords     = {{Efficient global optimization,Robust optimization,Bayesian,optimization,Gaussian process}},
  language     = {{eng}},
  number       = {{3}},
  pages        = {{693--711}},
  title        = {{A robust multi-objective Bayesian optimization framework considering input uncertainty}},
  url          = {{http://doi.org/10.1007/s10898-022-01262-9}},
  volume       = {{86}},
  year         = {{2023}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: