Likelihood ratio gradient estimation for stochastic recursions

Likelihood ratio gradient estimation for stochastic recursions

0.00 Avg rating0 Votes
Article ID: iaor1997273
Country: United Kingdom
Volume: 27
Issue: 4
Start Page Number: 1019
End Page Number: 1053
Publication Date: Dec 1995
Journal: Advances in Applied Probability
Authors: ,
Abstract:

In this paper, the authors develop mathematical machinery for verifying that a broad class of general state space Markov chains reacts smoothly to certain types of perturbations in the underlying transition structure. The main result provides conditions under which the stationary probability measure of an ergodic Harris-recurrent Markov chain is differentiable in a certain strong sense. The approach is based on likelihood ratio ‘change-of-measure’ arguments, and leads directly to a ‘likelihood ratio gradient estimator’ that can be computed numerically.

Reviews

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 Your email address will not be published.