A comparison of cross-entropy and variance minimization strategies

Chan, JCC; Glynn, PW; Kroese, DP

A comparison of cross-entropy and variance minimization strategies

Chan, JCC

Glynn, PW Kroese, DP

Permalink

Publication Type:: Journal Article
Citation:: Journal of Applied Probability, 2011, 48A pp. 183 - 194
Issue Date:: 2011-01-01

Closed Access

	Filename	Description	Size
	euclid.jap.1318940464.pdf	Published Version	139.54 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Chan, JCC https://orcid.org/0000-0003-3632-128X	en_US
dc.contributor.author	Glynn, PW	en_US
dc.contributor.author	Kroese, DP	en_US
dc.date.issued	2011-01-01	en_US
dc.identifier.citation	Journal of Applied Probability, 2011, 48A pp. 183 - 194	en_US
dc.identifier.issn	0021-9002	en_US
dc.identifier.uri	http://hdl.handle.net/10453/116096
dc.description.abstract	The variance minimization (VM) and cross-entropy (CE) methods are two versatile adaptive importance sampling procedures that have been successfully applied to a wide variety of difficult rare-event estimation problems. We compare these two methods via various examples where the optimal VM and CE importance densities can be obtained analytically. We find that in the cases studied both VM and CE methods prescribe the same importance sampling parameters, suggesting that the criterion of minimizing the CE distance is very close, if not asymptotically identical, to minimizing the variance of the associated importance sampling estimator. © 2011 Applied Probability Trust.	en_US
dc.relation.ispartof	Journal of Applied Probability	en_US
dc.relation.isbasedon	10.1239/jap/1318940464	en_US
dc.subject.classification	Statistics & Probability	en_US
dc.title	A comparison of cross-entropy and variance minimization strategies	en_US
dc.type	Journal Article
utslib.citation.volume	48A	en_US
utslib.for	0102 Applied Mathematics	en_US
utslib.for	0104 Statistics	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Business
pubs.organisational-group	/University of Technology Sydney/Faculty of Business/Economics Discipline
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	48A	en_US

Abstract:

The variance minimization (VM) and cross-entropy (CE) methods are two versatile adaptive importance sampling procedures that have been successfully applied to a wide variety of difficult rare-event estimation problems. We compare these two methods via various examples where the optimal VM and CE importance densities can be obtained analytically. We find that in the cases studied both VM and CE methods prescribe the same importance sampling parameters, suggesting that the criterion of minimizing the CE distance is very close, if not asymptotically identical, to minimizing the variance of the associated importance sampling estimator. © 2011 Applied Probability Trust.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/116096