Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources

Marcclo J. Weinberger; Meir Feder; Jorma Rissanen

Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources

Marcclo J. Weinberger^*, Meir Feder, Jorma Rissanen

^*Corresponding author for this work

Technion-Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The authors consider sequential universal coding of finite-state-machine (FSM) probabilistic sources. A fully sequential compression algorithm is presented which is shown not to be efficient. In a related work, the authors have considered the effective context algorithm and have shown that for the restricted class of tree sources its average code length also approaches the entropy at the optimal rate.

Original language	English
Title of host publication	Proceedings of the 1993 IEEE International Symposium on Information Theory
Publisher	Publ by IEEE
Pages	52
Number of pages	1
ISBN (Print)	0780308786
State	Published - 1993
Externally published	Yes
Event	Proceedings of the 1993 IEEE International Symposium on Information Theory - San Antonio, TX, USA Duration: 17 Jan 1993 → 22 Jan 1993

Publication series

Name	Proceedings of the 1993 IEEE International Symposium on Information Theory

Conference

Conference	Proceedings of the 1993 IEEE International Symposium on Information Theory
City	San Antonio, TX, USA
Period	17/01/93 → 22/01/93

Cite this

@inproceedings{6e979f79fbe04487a71f607f6cb91b82,

title = "Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources",

abstract = "The authors consider sequential universal coding of finite-state-machine (FSM) probabilistic sources. A fully sequential compression algorithm is presented which is shown not to be efficient. In a related work, the authors have considered the effective context algorithm and have shown that for the restricted class of tree sources its average code length also approaches the entropy at the optimal rate.",

author = "Weinberger, {Marcclo J.} and Meir Feder and Jorma Rissanen",

year = "1993",

language = "אנגלית",

isbn = "0780308786",

series = "Proceedings of the 1993 IEEE International Symposium on Information Theory",

publisher = "Publ by IEEE",

pages = "52",

booktitle = "Proceedings of the 1993 IEEE International Symposium on Information Theory",

note = "Proceedings of the 1993 IEEE International Symposium on Information Theory ; Conference date: 17-01-1993 Through 22-01-1993",

}

Weinberger, MJ, Feder, M & Rissanen, J 1993, Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources. in Proceedings of the 1993 IEEE International Symposium on Information Theory. Proceedings of the 1993 IEEE International Symposium on Information Theory, Publ by IEEE, pp. 52, Proceedings of the 1993 IEEE International Symposium on Information Theory, San Antonio, TX, USA, 17/01/93.

Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources. / Weinberger, Marcclo J.; Feder, Meir; Rissanen, Jorma.
Proceedings of the 1993 IEEE International Symposium on Information Theory. Publ by IEEE, 1993. p. 52 (Proceedings of the 1993 IEEE International Symposium on Information Theory).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources

AU - Weinberger, Marcclo J.

AU - Feder, Meir

AU - Rissanen, Jorma

PY - 1993

Y1 - 1993

N2 - The authors consider sequential universal coding of finite-state-machine (FSM) probabilistic sources. A fully sequential compression algorithm is presented which is shown not to be efficient. In a related work, the authors have considered the effective context algorithm and have shown that for the restricted class of tree sources its average code length also approaches the entropy at the optimal rate.

AB - The authors consider sequential universal coding of finite-state-machine (FSM) probabilistic sources. A fully sequential compression algorithm is presented which is shown not to be efficient. In a related work, the authors have considered the effective context algorithm and have shown that for the restricted class of tree sources its average code length also approaches the entropy at the optimal rate.

UR - http://www.scopus.com/inward/record.url?scp=0027152947&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:0027152947

SN - 0780308786

T3 - Proceedings of the 1993 IEEE International Symposium on Information Theory

SP - 52

BT - Proceedings of the 1993 IEEE International Symposium on Information Theory

PB - Publ by IEEE

T2 - Proceedings of the 1993 IEEE International Symposium on Information Theory

Y2 - 17 January 1993 through 22 January 1993

ER -

Sequential model estimation for universal coding and the predictive stochastic complexity of finite-state sources

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this