Access

You are not currently logged in.

Access JSTOR through your library or other institution:

login

Log in through your institution.

Journal Article

On the Interchange of Derivative and Expectation for Likelihood Ratio Derivative Estimators

Pierre L'Ecuyer
Management Science
Vol. 41, No. 4 (Apr., 1995), pp. 738-748
Published by: INFORMS
Stable URL: http://www.jstor.org/stable/2632893
Page Count: 11
Were these topics helpful?
See something inaccurate? Let us know!

Select the topics that are inaccurate.

Cancel
  • Download ($30.00)
  • Add to My Lists
  • Cite this Item
On the Interchange of Derivative and Expectation for Likelihood Ratio Derivative Estimators
Preview not available

Abstract

Sufficient conditions for the validity of interchange between derivative and expectation, in the context of likelihood ratio gradient estimation, were given in L'Ecuyer (1990). The aim of this paper is to shed additional light on these conditions and introduce specific variants of them, which are often easier to check. Sufficient conditions for the derivative estimator to have finite moments up to a given order are also given and illustrated by examples. In particular, we give an example of an unbiased derivative estimator which satisfies the interchange conditions but which has infinite variance.

Page Thumbnails

  • Thumbnail: Page 
738
    738
  • Thumbnail: Page 
739
    739
  • Thumbnail: Page 
740
    740
  • Thumbnail: Page 
741
    741
  • Thumbnail: Page 
742
    742
  • Thumbnail: Page 
743
    743
  • Thumbnail: Page 
744
    744
  • Thumbnail: Page 
745
    745
  • Thumbnail: Page 
746
    746
  • Thumbnail: Page 
747
    747
  • Thumbnail: Page 
748
    748