Convergence of profile based estimators

A. Orlitsky, N. Santhanam, K. Viswanathan, J. Zhang

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

9 Scopus citations

Abstract

We consider estimating distributions and their functions when the alphabet size is large compared to the amount of data observed. We establish consistency results and rates of convergence for estimators based on the data's profile - the number of symbols appearing any given number of times, and compare them with those based on empirical-frequency.

Original languageEnglish (US)
Title of host publicationProceedings of the 2005 IEEE International Symposium on Information Theory, ISIT 05
Pages1843-1847
Number of pages5
DOIs
StatePublished - 2005
Externally publishedYes
Event2005 IEEE International Symposium on Information Theory, ISIT 05 - Adelaide, Australia
Duration: Sep 4 2005Sep 9 2005

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2005
ISSN (Print)2157-8099

Other

Other2005 IEEE International Symposium on Information Theory, ISIT 05
Country/TerritoryAustralia
CityAdelaide
Period9/4/059/9/05

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Convergence of profile based estimators'. Together they form a unique fingerprint.

Cite this