On performance potentials and conditional Monte Carlo for gradient estimation for Markov chains

On performance potentials and conditional Monte Carlo for gradient estimation for Markov chains

0.00 Avg rating0 Votes
Article ID: iaor2000414
Country: Netherlands
Volume: 87
Issue: 1
Start Page Number: 263
End Page Number: 272
Publication Date: Apr 1999
Journal: Annals of Operations Research
Authors: , ,
Abstract:

We consider the problem of sample path-based gradient estimation for long-run (steady-state) performance measures defined on discrete-time Markov chains. We show how two estimators – one derived using the likelihood ratio method with conditional Monte Carlo and splitting, and the other derived using performance potentials and perturbation analysis – are related. In particular, one can be expressed as the conditional expectation of a suitably weighted average of the other. This demonstrates yet another connection between the two gradient estimation techniques of perturbation analysis and the likelihood ratio method.

Reviews

Required fields are marked *. Your email address will not be published.