Measure-Valued Differentiation for Markov Chains

B. Heidergott () and F. J. Vázquez-Abad
Additional contact information
B. Heidergott: Vrije Universiteit and Tinbergen Institute
F. J. Vázquez-Abad: University of Melbourne

Journal of Optimization Theory and Applications, 2008, vol. 136, issue 2, No 3, 187-209

Abstract: Abstract This paper addresses the problem of sensitivity analysis for finite-horizon performance measures of general Markov chains. We derive closed-form expressions and associated unbiased gradient estimators for the derivatives of finite products of Markov kernels by measure-valued differentiation (MVD). In the MVD setting, the derivatives of Markov kernels, called $\mathcal{D}$ -derivatives, are defined with respect to a class of performance functions $\mathcal{D}$ such that, for any performance measure $g\in\mathcal{D}$ , the derivative of the integral of g with respect to the one-step transition probability of the Markov chain exists. The MVD approach (i) yields results that can be applied to performance functions out of a predefined class, (ii) allows for a product rule of differentiation, that is, analyzing the derivative of the transition kernel immediately yields finite-horizon results, (iii) provides an operator language approach to the differentiation of Markov chains and (iv) clearly identifies the trade-off between the generality of the performance classes that can be analyzed and the generality of the classes of measures (Markov kernels). The $\mathcal{D}$ -derivative of a measure can be interpreted in terms of various (unbiased) gradient estimators and the product rule for $\mathcal {D}$ -differentiation yields a product-rule for various gradient estimators.

Keywords: Gradient estimation; Simulation; Perturbation analysis; Measure-valued differentiation (search for similar items in EconPapers)
Date: 2008
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://link.springer.com/10.1007/s10957-007-9297-7 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joptap:v:136:y:2008:i:2:d:10.1007_s10957-007-9297-7

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1007/s10957-007-9297-7

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().