Fast computation of the kullback-leibler divergence and exact fisher information for the first-order moving average model

Enes Makalic; Daniel F. Schmidt

doi:10.1109/LSP.2009.2039659

Fast computation of the kullback-leibler divergence and exact fisher information for the first-order moving average model

Research output: Contribution to journal › Article › Research › peer-review

Abstract

In this note expressions are derived that allow computation of the Kullback-Leibler (K-L) divergence between two first-order Gaussian moving average models in O_n(1) time as the sample size n →∞. These expressions can also be used to evaluate the exact Fisher information matrix in O_n(1)time, and provide a basis for an asymptotic expression of the K-L divergence.

Original language	English
Article number	5371931
Pages (from-to)	391-393
Number of pages	3
Journal	IEEE Signal Processing Letters
Volume	17
Issue number	4
DOIs	https://doi.org/10.1109/LSP.2009.2039659
Publication status	Published - 2010
Externally published	Yes

Access to Document

10.1109/LSP.2009.2039659

Cite this

@article{a66b9fab8b6845bc84fd207e6fd6ac1c,

title = "Fast computation of the kullback-leibler divergence and exact fisher information for the first-order moving average model",

abstract = "In this note expressions are derived that allow computation of the Kullback-Leibler (K-L) divergence between two first-order Gaussian moving average models in On(1) time as the sample size n →∞. These expressions can also be used to evaluate the exact Fisher information matrix in On(1)time, and provide a basis for an asymptotic expression of the K-L divergence.",

author = "Enes Makalic and Schmidt, \{Daniel F.\}",

year = "2010",

doi = "10.1109/LSP.2009.2039659",

language = "English",

volume = "17",

pages = "391--393",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

number = "4",

}

TY - JOUR

T1 - Fast computation of the kullback-leibler divergence and exact fisher information for the first-order moving average model

AU - Makalic, Enes

AU - Schmidt, Daniel F.

PY - 2010

Y1 - 2010

N2 - In this note expressions are derived that allow computation of the Kullback-Leibler (K-L) divergence between two first-order Gaussian moving average models in On(1) time as the sample size n →∞. These expressions can also be used to evaluate the exact Fisher information matrix in On(1)time, and provide a basis for an asymptotic expression of the K-L divergence.

AB - In this note expressions are derived that allow computation of the Kullback-Leibler (K-L) divergence between two first-order Gaussian moving average models in On(1) time as the sample size n →∞. These expressions can also be used to evaluate the exact Fisher information matrix in On(1)time, and provide a basis for an asymptotic expression of the K-L divergence.

UR - https://www.scopus.com/pages/publications/78651370710

U2 - 10.1109/LSP.2009.2039659

DO - 10.1109/LSP.2009.2039659

M3 - Article

AN - SCOPUS:78651370710

SN - 1070-9908

VL - 17

SP - 391

EP - 393

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 4

M1 - 5371931

ER -

Fast computation of the kullback-leibler divergence and exact fisher information for the first-order moving average model

Abstract

Access to Document

Other files and links

Cite this