A new gradient-free active subspace estimation method with application to rare event probability estimation
ESAIM: Probability and Statistics · 04.11.2026
DOI: 10.1051/ps/2026024 ↗Kurz gefasst
Fachartikel in der Zeitschrift ESAIM: Probability and Statistics, online erschienen am 04.11.2026. Verfasst von Valentin Breaz und 3 weiteren Autor:innen. Gefördert von: CIROQUO.
Abstract (Originalsprache)
To reduce the cost of estimating the probability of a rare event involving a very large number of random parameters, we propose a new strategy for dimension reduction coupled with a surrogate model for the expensive part of the algorithm. To this end, we extend the Ordinary Kriging Active Subspace (OK-AS) method into a sequential version. Our approach consists of iteratively re-estimating the active subspace using a Kriging surrogate trained in a rotated coordinate system until the active subspace stabilises. This method allows for a reduction in prediction error and a better approximation of the active subspace on a benchmark of test problems. Furthermore, we integrate our algorithm into an efficient pre-existing approach for estimating the probability of a rare event. This approach is based on learning the active subspace associated with the random event whose probability is to be estimated. The sequential learning of an importance sampling density is necessary and corresponds to the expensive part of this strategy. To circumvent this, we integrate our sequential OK-AS version into the estimation of the importance sampling density. The numerical results indicate that our method allows for reducing the cost required to obtain a precise estimate of the rare event probability.
Förderung
- CIROQUO
Zitieren
APA
Breaz, V., Zuniga, M. M., Zahm, O., & Wilkinson, R. (2026). A new gradient-free active subspace estimation method with application to rare event probability estimation. ESAIM: Probability and Statistics. https://doi.org/10.1051/ps/2026024
Vancouver
Breaz V, Zuniga MM, Zahm O, Wilkinson R. A new gradient-free active subspace estimation method with application to rare event probability estimation. ESAIM: Probability and Statistics. 2026. doi:10.1051/ps/2026024
BibTeX
@article{Breaz2026,
author = {Breaz, Valentin and Zuniga, Miguel Munoz and Zahm, Olivier and Wilkinson, Richard},
title = {A new gradient-free active subspace estimation method with application to rare event probability estimation},
journal = {ESAIM: Probability and Statistics},
year = {2026},
doi = {10.1051/ps/2026024}
}
EUVIMED