EUVIMEDEUVIMED entdecken
Crossref

Cross-Validation--based Adaptive Sampling for Gaussian Process Models

Hossein Mohammadi, Peter Challenor, Daniel Williamson, Marc Goodfellow

SIAM/ASA Journal on Uncertainty Quantification · 2022-03 · 10 (1) · 294-316

DOI: 10.1137/21m1404260 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM/ASA Journal on Uncertainty Quantification, online erschienen am 28.02.2022. Verfasst von Hossein Mohammadi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In many real-world applications, we are interested in approximating black-box, costly functions as accurately as possible with the smallest number of function evaluations. A complex computer code is an example of such a function. In this work, a Gaussian process (GP) emulator is used to approximate the output of complex computer code. We consider the problem of extending an initial experiment (set of model runs) sequentially to improve the emulator. A sequential sampling approach based on leave-one-out (LOO) cross-validation is proposed that can be easily extended to a batch mode. This is a desirable property since it saves the user time when parallel computing is available. After fitting a GP to training data points, the expected squared LOO (ES-LOO) error is calculated at each design point. ES-LOO is used as a measure to identify important data points. More precisely, when this quantity is large at a point it means that the quality of prediction depends a great deal on that point and adding more samples nearby could improve the accuracy of the GP. As a result, it is reasonable to select the next sample where ES-LOO is maximized. However, ES-LOO is only known at the experimental design and needs to be estimated at unobserved points. To do this, a second GP is fitted to the ES-LOO errors, and where the maximum of the modified expected improvement (EI) criterion occurs is chosen as the next sample. EI is a popular acquisition function in Bayesian optimization and is used to trade off between local and global search. However, it has a tendency towards exploitation, meaning that its maximum is close to the (current) “best" sample. To avoid clustering, a modified version of EI, called pseudoexpected improvement, is employed which is more explorative than EI yet allows us to discover unexplored regions. Our results show that the proposed sampling method is promising.

Förderung

  • Engineering and Physical Sciences Research Council

Zitieren

APA

Mohammadi, H., Challenor, P., Williamson, D., & Goodfellow, M. (2022). Cross-Validation--based Adaptive Sampling for Gaussian Process Models. SIAM/ASA Journal on Uncertainty Quantification, 10(1), 294-316. https://doi.org/10.1137/21m1404260

Vancouver

Mohammadi H, Challenor P, Williamson D, Goodfellow M. Cross-Validation--based Adaptive Sampling for Gaussian Process Models. SIAM/ASA Journal on Uncertainty Quantification. 2022;10(1):294-316. doi:10.1137/21m1404260

BibTeX
@article{Mohammadi2022,
  author = {Mohammadi, Hossein and Challenor, Peter and Williamson, Daniel and Goodfellow, Marc},
  title = {Cross-Validation--based Adaptive Sampling for Gaussian Process Models},
  journal = {SIAM/ASA Journal on Uncertainty Quantification},
  year = {2022},
  volume = {10},
  number = {1},
  pages = {294--316},
  doi = {10.1137/21m1404260}
}
Kostenlos starten →