Joint universal lossy coding and identification of stationary mixing sources

Maxim Raginsky

doi:10.1109/ISIT.2007.4557508

Joint universal lossy coding and identification of stationary mixing sources

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The problem of joint universal source coding and modeling, treated in the context of lossless codes by Rissanen, was recently generalized to fixed-rate lossy coding of finitely parametrized continuous-alphabet i.i.d. sources. We extend these results to variable-rate lossy block coding of stationary ergodic sources and show that, for bounded metric distortion measures, any finitely parametrized family of stationary sources satisfying suitable mixing, smoothness and Vapnik-Chervonenkis learnability conditions admits universal schemes for joint lossy source coding and identification. We also give several explicit examples of parametric sources satisfying the regularity conditions.

Original language	English (US)
Title of host publication	Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007
Pages	1961-1965
Number of pages	5
DOIs	https://doi.org/10.1109/ISIT.2007.4557508
State	Published - 2007
Event	2007 IEEE International Symposium on Information Theory, ISIT 2007 - Nice, France Duration: Jun 24 2007 → Jun 29 2007

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings
ISSN (Print)	2157-8101

Other

Other	2007 IEEE International Symposium on Information Theory, ISIT 2007
Country/Territory	France
City	Nice
Period	6/24/07 → 6/29/07

ASJC Scopus subject areas

Theoretical Computer Science
Information Systems
Modeling and Simulation
Applied Mathematics

Online availability

10.1109/ISIT.2007.4557508

Library availability

Discover UIUC Full Text

Cite this

Raginsky, M 2007, Joint universal lossy coding and identification of stationary mixing sources. in Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007., 4557508, IEEE International Symposium on Information Theory - Proceedings, pp. 1961-1965, 2007 IEEE International Symposium on Information Theory, ISIT 2007, Nice, France, 6/24/07. https://doi.org/10.1109/ISIT.2007.4557508

@inproceedings{94d0ac858b494e6e8a4705d0dcfc096e,

title = "Joint universal lossy coding and identification of stationary mixing sources",

abstract = "The problem of joint universal source coding and modeling, treated in the context of lossless codes by Rissanen, was recently generalized to fixed-rate lossy coding of finitely parametrized continuous-alphabet i.i.d. sources. We extend these results to variable-rate lossy block coding of stationary ergodic sources and show that, for bounded metric distortion measures, any finitely parametrized family of stationary sources satisfying suitable mixing, smoothness and Vapnik-Chervonenkis learnability conditions admits universal schemes for joint lossy source coding and identification. We also give several explicit examples of parametric sources satisfying the regularity conditions.",

author = "Maxim Raginsky",

year = "2007",

doi = "10.1109/ISIT.2007.4557508",

language = "English (US)",

isbn = "1424414296",

series = "IEEE International Symposium on Information Theory - Proceedings",

pages = "1961--1965",

booktitle = "Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007",

note = "2007 IEEE International Symposium on Information Theory, ISIT 2007 ; Conference date: 24-06-2007 Through 29-06-2007",

}

TY - GEN

T1 - Joint universal lossy coding and identification of stationary mixing sources

AU - Raginsky, Maxim

PY - 2007

Y1 - 2007

N2 - The problem of joint universal source coding and modeling, treated in the context of lossless codes by Rissanen, was recently generalized to fixed-rate lossy coding of finitely parametrized continuous-alphabet i.i.d. sources. We extend these results to variable-rate lossy block coding of stationary ergodic sources and show that, for bounded metric distortion measures, any finitely parametrized family of stationary sources satisfying suitable mixing, smoothness and Vapnik-Chervonenkis learnability conditions admits universal schemes for joint lossy source coding and identification. We also give several explicit examples of parametric sources satisfying the regularity conditions.

AB - The problem of joint universal source coding and modeling, treated in the context of lossless codes by Rissanen, was recently generalized to fixed-rate lossy coding of finitely parametrized continuous-alphabet i.i.d. sources. We extend these results to variable-rate lossy block coding of stationary ergodic sources and show that, for bounded metric distortion measures, any finitely parametrized family of stationary sources satisfying suitable mixing, smoothness and Vapnik-Chervonenkis learnability conditions admits universal schemes for joint lossy source coding and identification. We also give several explicit examples of parametric sources satisfying the regularity conditions.

UR - http://www.scopus.com/inward/record.url?scp=46849089658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46849089658&partnerID=8YFLogxK

U2 - 10.1109/ISIT.2007.4557508

DO - 10.1109/ISIT.2007.4557508

M3 - Conference contribution

AN - SCOPUS:46849089658

SN - 1424414296

SN - 9781424414291

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 1961

EP - 1965

BT - Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007

T2 - 2007 IEEE International Symposium on Information Theory, ISIT 2007

Y2 - 24 June 2007 through 29 June 2007

ER -

Joint universal lossy coding and identification of stationary mixing sources

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this