Result: Perturbation analysis via coupling

Title:
Perturbation analysis via coupling
Authors:
Liyi Dai
Source:
IFAC Proceedings Volumes. 32:4753-4758
Publisher Information:
Elsevier BV, 1998.
Publication Year:
1998
Subject Terms:
0209 industrial biotechnology, Computational methods in stochastic control, Markov chains, 0203 mechanical engineering, Numerical analysis or methods applied to Markov chains, gradient estimation, perturbation analysis, 02 engineering and technology, coupling, Numerical methods based on necessary conditions
Document Type:
Academic journal Article
File Description:
application/xml
Language:
English
ISSN:
1474-6670
DOI:
10.1016/s1474-6670(17)56810-x
DOI:
10.1117/12.319338
DOI:
10.1109/9.847099
Access URL:
https://zbmath.org/1518624
https://doi.org/10.1109/9.847099
https://www.sciencedirect.com/science/article/pii/S147466701756810X
https://ieeexplore.ieee.org/document/847099
https://dblp.uni-trier.de/db/journals/tac/tac45.html#Dai00
http://ui.adsabs.harvard.edu/abs/1998SPIE.3369..230D/abstract
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/3369/1/Perturbation-analysis-via-coupling/10.1117/12.319338.full
Rights:
Elsevier TDM
IEEE Copyright
Accession Number:
edsair.doi.dedup.....2152b2e200fe0cfdba80f9fd7aa10c20
Database:
OpenAIRE

Further Information

The problem of gradient estimation consists in obtaining an estimate of \(J'(\theta)\) from a sample of \(X_\theta\), where \(X_\theta\) is a parameterized random variable, \(\theta\in (a,b)\subset \mathbb{R}\), \(J(\theta)= E[L(X_\theta)]\), \(L(x): \mathbb{R}\to\mathbb{R}\). A few general gradient estimators are derived using perturbation analysis via coupling. Specifically, the coupling method is applied to gradient estimation of Markov chains.