DocumentCode
2945883
Title
The Universal Measure for General Sources and Its Application to MDL/Bayesian Criteria
Author
Suzuki, Joe
Author_Institution
Dept. of Math., Osaka Univ., Toyonaka, Japan
fYear
2011
fDate
29-31 March 2011
Firstpage
478
Lastpage
478
Abstract
Summary form only given. We derive the most generalized universal coding and consider its application to the MDL principle.
Keywords
Bayes methods; encoding; Bayesian Criteria; MDL criteria; minimum description length criteria; universal coding; Channel coding; Data compression; Markov processes; Time series analysis; Radon-Nykodim derivative; Shannon-McMillan-Breiman theorem; minimum description principle; universal coding;
fLanguage
English
Publisher
ieee
Conference_Titel
Data Compression Conference (DCC), 2011
Conference_Location
Snowbird, UT
ISSN
1068-0314
Print_ISBN
978-1-61284-279-0
Type
conf
DOI
10.1109/DCC.2011.82
Filename
5749535
Link To Document