Convergence of profile based estimators

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

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

7 Citations (Scopus)

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 publicationIEEE International Symposium on Information Theory - Proceedings
Pages1843-1847
Number of pages5
Volume2005
DOIs
StatePublished - 2005
Externally publishedYes
Event2005 IEEE International Symposium on Information Theory, ISIT 05 - Adelaide, Australia
Duration: Sep 4 2005Sep 9 2005

Other

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

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Orlitsky, A., Santhanam, N., Viswanathan, K., & Zhang, J. (2005). Convergence of profile based estimators. In IEEE International Symposium on Information Theory - Proceedings (Vol. 2005, pp. 1843-1847). [1523664] https://doi.org/10.1109/ISIT.2005.1523664

Convergence of profile based estimators. / Orlitsky, A.; Santhanam, N.; Viswanathan, K.; Zhang, Junan.

IEEE International Symposium on Information Theory - Proceedings. Vol. 2005 2005. p. 1843-1847 1523664.

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

Orlitsky, A, Santhanam, N, Viswanathan, K & Zhang, J 2005, Convergence of profile based estimators. in IEEE International Symposium on Information Theory - Proceedings. vol. 2005, 1523664, pp. 1843-1847, 2005 IEEE International Symposium on Information Theory, ISIT 05, Adelaide, Australia, 9/4/05. https://doi.org/10.1109/ISIT.2005.1523664
Orlitsky A, Santhanam N, Viswanathan K, Zhang J. Convergence of profile based estimators. In IEEE International Symposium on Information Theory - Proceedings. Vol. 2005. 2005. p. 1843-1847. 1523664 https://doi.org/10.1109/ISIT.2005.1523664
Orlitsky, A. ; Santhanam, N. ; Viswanathan, K. ; Zhang, Junan. / Convergence of profile based estimators. IEEE International Symposium on Information Theory - Proceedings. Vol. 2005 2005. pp. 1843-1847
@inproceedings{04377393cf764162b054b438716a2963,
title = "Convergence of profile based estimators",
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.",
author = "A. Orlitsky and N. Santhanam and K. Viswanathan and Junan Zhang",
year = "2005",
doi = "10.1109/ISIT.2005.1523664",
language = "English (US)",
isbn = "0780391519",
volume = "2005",
pages = "1843--1847",
booktitle = "IEEE International Symposium on Information Theory - Proceedings",

}

TY - GEN

T1 - Convergence of profile based estimators

AU - Orlitsky, A.

AU - Santhanam, N.

AU - Viswanathan, K.

AU - Zhang, Junan

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=33749438094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749438094&partnerID=8YFLogxK

U2 - 10.1109/ISIT.2005.1523664

DO - 10.1109/ISIT.2005.1523664

M3 - Conference contribution

SN - 0780391519

SN - 9780780391512

VL - 2005

SP - 1843

EP - 1847

BT - IEEE International Symposium on Information Theory - Proceedings

ER -