Hostname: page-component-7b7567c8c-fvjsw Total loading time: 0 Render date: 2026-11-15T16:03:50.711Z Has data issue: false hasContentIssue false
  • English
  • Français

Semiparametric cross entropy for rare-event simulation

Part of:Probabilistic methods, simulation and stochastic differential equations

Published online by Cambridge University Press:  24 October 2016

Z. I. Botev,
A. Ridder and
L. Rojas-Nandayapa
Z. I. Botev*
Affiliation:
The University of New South Wales
A. Ridder*
Affiliation:
Vrije Universiteit
L. Rojas-Nandayapa*
Affiliation:
The University of Queensland
*
*Postal address: School of Mathematics and Statistics, University of New South Wales, Sydney, NSW 2052, Australia. Email address: botev@unsw.edu.au
** Postal address: School of Mathematics and Physics, The University of Queensland, Brisbane, QLD 4072, Australia.
*** Postal address: Department of Econometrics and Operations Research, Vrije Universiteit, 1081 HV, Amsterdam, The Netherlands.
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

The cross entropy is a well-known adaptive importance sampling method which requires estimating an optimal importance sampling distribution within a parametric class. In this paper we analyze an alternative version of the cross entropy, where the importance sampling distribution is selected instead within a general semiparametric class of distributions. We show that the semiparametric cross entropy method delivers efficient estimators in a wide variety of rare-event problems. We illustrate the favourable performance of the method with numerical experiments.

Keywords

Light-tailedregularly-varyingsubexponentialrare-event probabilitycross entropy method

MSC classification

Primary:65C05: Monte Carlo methods
Secondary:65C60: Computational problems in statistics65C40: Computational Markov chains

Information

Type
Research Papers
Information
Journal of Applied Probability , Volume 53 , Issue 3 , September 2016, pp. 633 - 649
Copyright
Copyright © Applied Probability Trust 2016 

References

[1] Asmussen, S. and Glynn, P. W. (2007).Stochastic Simulation: Algorithms and Analysis,Springer,New York.Google Scholar
[2] Asmussen, S. and Kroese, D. P. (2006).Improved algorithms for rare event simulation with heavy tails.Adv. Appl. Prob. 38,545–558.Google Scholar
[3] Asmussen, S.,Kroese, D. P. and Rubinstein, R. Y. (2005).Heavy tails, importance sampling and cross-entropy.Stoch. Models 21,57–76.Google Scholar
[4] Botev, Z. I. and Kroese, D. P. (2012).Efficient Monte Carlo simulation via the generalized splitting method.Statist. Comput. 22,1–16.Google Scholar
[5] Botev, Z. I.,L'Ecuyer, P. and Tuffin, B. (2013).Markov chain importance sampling with applications to rare event probability estimation.Statist. Comput. 23,271–285.Google Scholar
[6] Chan, J. C. C.,Glynn, P. W. and Kroese, D. P. (2011).A comparison of cross-entropy and variance minimization strategies. In New Frontiers in Applied Probability (J. Appl. Prob. Spec. Vol. 48A),New Frontiers in Applied Probability Applied Probability Trust,Sheffield, pp.183–194.Google Scholar
[7] Dupuis, P. Leder, K. Wang, H. (2007).Importance sampling for sums of random variables with regularly varying tails.ACM TOMACS 17,14.Google Scholar
[8] Embrechts, P. and Goldie, C. M. (1980).On closure and factorization properties of subexponential and related distributions.J. Austral. Math. Soc. A 29,243–256.Google Scholar
[9] Embrechts, P.,Kluppelberg, C. and Mikosch, T. (1997).Modelling Extremal Events.Springer,Berlin.Google Scholar
[10] Foss, S.,Korshunov, D. and Zachary, S. (2011).An Introduction to Heavy-Tailed and Subexponential Distributions,Springer,New York.Google Scholar
[11] Ghamami, S. and Ross, S. M. (2012). Improving the Asmussen–Kroese-type simulation estimators.J. Appl. Prob. 49,1188–1193.Google Scholar
[12] Gudmundsson, T. and Hult, H. (2014).Markov chain Monte Carlo for computing rare-event probabilities for a heavy-tailed random walk.J. Appl. Prob. 51,359–376.Google Scholar
[13] Juneja, S. (2007).Estimating tail probabilities of heavy tailed distributions with asymptotically zero relative error.Queueing Systems 57,115–127.Google Scholar
[14] Perrakis, K.,Ntzoufras, I. and Tsionas, E. G. (2014).On the use of marginal posteriors in marginal likelihood estimation via importance sampling.Comput. Statist. Data Anal. 77,54–69.Google Scholar
[15] Wong, R.(2001).Asymptotic Approximation of Integrals (Classics Appl. Math. 34).Society for Industrial and Applied Mathematics,Philidelphia, PA..Google Scholar