ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1601.02557
67
68
v1v2v3 (latest)

Bayesian subset simulation

11 January 2016
Julien Bect
Ling Li
E. Vázquez
ArXiv (abs)PDFHTML
Abstract

We consider the problem of estimating a probability of failure α\alphaα, defined as the volume of the excursion set of a function f:X⊆Rd→Rf:\mathbb{X} \subseteq \mathbb{R}^{d} \to \mathbb{R}f:X⊆Rd→R above a given threshold, under a given probability measure on X\mathbb{X}X. In this article, we combine the popular subset simulation algorithm (Au and Beck, Probab. Eng. Mech. 2001) and our sequential Bayesian approach for the estimation of a probability of failure (Bect, Ginsbourger, Li, Picheny and Vazquez, Stat. Comput. 2012). This makes it possible to estimate α\alphaα when the number of evaluations of fff is very limited and α\alphaα is very small. The resulting algorithm is called Bayesian subset simulation (BSS). A key idea, as in the subset simulation algorithm, is to estimate the probabilities of a sequence of excursion sets of fff above intermediate thresholds, using a sequential Monte Carlo (SMC) approach. A Gaussian process prior on fff is used to define the sequence of densities targeted by the SMC algorithm, and drive the selection of evaluation points of fff to estimate the intermediate probabilities. Adaptive procedures are proposed to determine the intermediate thresholds and the number of evaluations to be carried out at each stage of the algorithm. Numerical experiments illustrate that BSS achieves significant savings in the number of function evaluations with respect to other Monte Carlo approaches.

View on arXiv
Comments on this paper