Universal coding of non-discrete sources based on distribution estimation consistent in expected information divergence

Andrew R. Barron, Laszlo Gyoerfi, Edward C. van der Meulen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An attempt is made to show how a certain given distribution estimator, which is consistent in expected information divergence, leads to a universal code for the class of all probability measures on a given nondiscrete space which are dominated in I-divergence by a known given probability measure.

Original languageEnglish
Title of host publicationProceedings of the 1993 IEEE International Symposium on Information Theory
PublisherPubl by IEEE
Number of pages1
ISBN (Print)0780308786
Publication statusPublished - Jan 1 1993
EventProceedings of the 1993 IEEE International Symposium on Information Theory - San Antonio, TX, USA
Duration: Jan 17 1993Jan 22 1993

Publication series

NameProceedings of the 1993 IEEE International Symposium on Information Theory

Other

OtherProceedings of the 1993 IEEE International Symposium on Information Theory
CitySan Antonio, TX, USA
Period1/17/931/22/93

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Barron, A. R., Gyoerfi, L., & van der Meulen, E. C. (1993). Universal coding of non-discrete sources based on distribution estimation consistent in expected information divergence. In Proceedings of the 1993 IEEE International Symposium on Information Theory (Proceedings of the 1993 IEEE International Symposium on Information Theory). Publ by IEEE.