SEMIPARAMETRIC CROSS ENTROPY FOR RARE-EVENT SIMULATION



Botev, ZI, Ridder, A and Rojas-Nandayapa, L ORCID: 0000-0001-5652-3183
(2016) SEMIPARAMETRIC CROSS ENTROPY FOR RARE-EVENT SIMULATION. JOURNAL OF APPLIED PROBABILITY, 53 (3). pp. 633-649.

[img] Text
1310.3596v1.pdf - Submitted version

Download (230kB)

Abstract

The Cross Entropy method is a well-known adaptive importance sampling method for rare-event probability estimation, which requires estimating an optimal importance sampling density within a parametric class. In this article we estimate an optimal importance sampling density within a wider semiparametric class of distributions. We show that this semiparametric version of the Cross Entropy method frequently yields efficient estimators. We illustrate the excellent practical performance of the method with numerical experiments and show that for the problems we consider it typically outperforms alternative schemes by orders of magnitude.

Item Type: Article
Additional Information: Source info: Tinbergen Institute Discussion Paper 13-127/III
Uncontrolled Keywords: Light-tailed, regularly-varying, subexponential, rare-event probability, cross entropy method
Depositing User: Symplectic Admin
Date Deposited: 04 Nov 2016 08:38
Last Modified: 19 Jan 2023 07:26
DOI: 10.1017/jpr.2016.31
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3004345