Schemes for bidirectional modeling of discrete stationary sources

Jiming Yu; Sergio Verdú

doi:10.1109/TIT.2006.883626

Schemes for bidirectional modeling of discrete stationary sources

Jiming Yu, Sergio Verdú

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

16 Scopus citations

Abstract

We develop adaptive schemes for bidirectional modeling of unknown discrete stationary sources. These algorithms can be applied to statistical inference problems such as noncausal universal discrete denoising that exploit bidirectional dependencies. Efficient algorithms for constructing those models are developed and we compare their performance to that of the DUDE algorithm for universal discrete denoising.

Original language	English (US)
Pages (from-to)	4789-4807
Number of pages	19
Journal	IEEE Transactions on Information Theory
Volume	52
Issue number	11
DOIs	https://doi.org/10.1109/TIT.2006.883626
State	Published - Nov 2006

All Science Journal Classification (ASJC) codes

Information Systems
Computer Science Applications
Library and Information Sciences

Keywords

Bidirectional modeling
Discrete stationary sources
Universal algorithms
Universal discrete denoising

Access to Document

10.1109/TIT.2006.883626

Cite this

@article{e65530313ede4ec78aa990002fa4175a,

title = "Schemes for bidirectional modeling of discrete stationary sources",

abstract = "We develop adaptive schemes for bidirectional modeling of unknown discrete stationary sources. These algorithms can be applied to statistical inference problems such as noncausal universal discrete denoising that exploit bidirectional dependencies. Efficient algorithms for constructing those models are developed and we compare their performance to that of the DUDE algorithm for universal discrete denoising.",

keywords = "Bidirectional modeling, Discrete stationary sources, Universal algorithms, Universal discrete denoising",

author = "Jiming Yu and Sergio Verd{\'u}",

note = "Funding Information: Manuscript received May 4, 2005; revised June 21, 2006. This work was partially supported by the National Science Foundation under Grant CCR-0312839. The material in this paper was presented in part at the Conference on Information Sciences and Systems, Baltimore, MD, March 2005.",

year = "2006",

month = nov,

doi = "10.1109/TIT.2006.883626",

language = "English (US)",

volume = "52",

pages = "4789--4807",

journal = "IEEE Transactions on Information Theory",

issn = "0018-9448",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "11",

}

TY - JOUR

T1 - Schemes for bidirectional modeling of discrete stationary sources

AU - Yu, Jiming

AU - Verdú, Sergio

N1 - Funding Information: Manuscript received May 4, 2005; revised June 21, 2006. This work was partially supported by the National Science Foundation under Grant CCR-0312839. The material in this paper was presented in part at the Conference on Information Sciences and Systems, Baltimore, MD, March 2005.

PY - 2006/11

Y1 - 2006/11

N2 - We develop adaptive schemes for bidirectional modeling of unknown discrete stationary sources. These algorithms can be applied to statistical inference problems such as noncausal universal discrete denoising that exploit bidirectional dependencies. Efficient algorithms for constructing those models are developed and we compare their performance to that of the DUDE algorithm for universal discrete denoising.

AB - We develop adaptive schemes for bidirectional modeling of unknown discrete stationary sources. These algorithms can be applied to statistical inference problems such as noncausal universal discrete denoising that exploit bidirectional dependencies. Efficient algorithms for constructing those models are developed and we compare their performance to that of the DUDE algorithm for universal discrete denoising.

KW - Bidirectional modeling

KW - Discrete stationary sources

KW - Universal algorithms

KW - Universal discrete denoising

UR - http://www.scopus.com/inward/record.url?scp=33750590426&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750590426&partnerID=8YFLogxK

U2 - 10.1109/TIT.2006.883626

DO - 10.1109/TIT.2006.883626

M3 - Article

AN - SCOPUS:33750590426

SN - 0018-9448

VL - 52

SP - 4789

EP - 4807

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

IS - 11

ER -

Schemes for bidirectional modeling of discrete stationary sources

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this