Asymptotically minimax regret by bayes mixtures

J. Takeuchi; A. R. Barron

doi:10.1109/ISIT.1998.708923

Asymptotically minimax regret by bayes mixtures

J. Takeuchi, A. R. Barron

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

25 Citations (Scopus)

Abstract

We study the problem of data compression, gambling and prediction of a sequence xⁿ = x₁x₂...x_n from a certain alphabet X, in terms of regret (Shtarkov 1988) and redundancy with respect to a general exponential family, a general smooth family, and also Markov sources. In particular, we show that variants of Jeffreys mixture asymptotically achieve their minimax values.

Original language	English
Title of host publication	Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998
Pages	318
Number of pages	1
DOIs	https://doi.org/10.1109/ISIT.1998.708923
Publication status	Published - 1998
Externally published	Yes
Event	1998 IEEE International Symposium on Information Theory, ISIT 1998 - Cambridge, MA, United States Duration: Aug 16 1998 → Aug 21 1998

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings
ISSN (Print)	2157-8095

Other

Other	1998 IEEE International Symposium on Information Theory, ISIT 1998
Country/Territory	United States
City	Cambridge, MA
Period	8/16/98 → 8/21/98

All Science Journal Classification (ASJC) codes

Theoretical Computer Science
Information Systems
Modelling and Simulation
Applied Mathematics

Access to Document

10.1109/ISIT.1998.708923

Cite this

Takeuchi, J & Barron, AR 1998, Asymptotically minimax regret by bayes mixtures. in Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998., 708923, IEEE International Symposium on Information Theory - Proceedings, pp. 318, 1998 IEEE International Symposium on Information Theory, ISIT 1998, Cambridge, MA, United States, 8/16/98. https://doi.org/10.1109/ISIT.1998.708923

@inproceedings{6930a59dfb0f49e0b99b9b56b21a8eaa,

title = "Asymptotically minimax regret by bayes mixtures",

abstract = "We study the problem of data compression, gambling and prediction of a sequence xn = x1x2...xn from a certain alphabet X, in terms of regret (Shtarkov 1988) and redundancy with respect to a general exponential family, a general smooth family, and also Markov sources. In particular, we show that variants of Jeffreys mixture asymptotically achieve their minimax values.",

author = "J. Takeuchi and Barron, {A. R.}",

year = "1998",

doi = "10.1109/ISIT.1998.708923",

language = "English",

isbn = "0780350006",

series = "IEEE International Symposium on Information Theory - Proceedings",

pages = "318",

booktitle = "Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998",

note = "1998 IEEE International Symposium on Information Theory, ISIT 1998 ; Conference date: 16-08-1998 Through 21-08-1998",

}

TY - GEN

T1 - Asymptotically minimax regret by bayes mixtures

AU - Takeuchi, J.

AU - Barron, A. R.

PY - 1998

Y1 - 1998

N2 - We study the problem of data compression, gambling and prediction of a sequence xn = x1x2...xn from a certain alphabet X, in terms of regret (Shtarkov 1988) and redundancy with respect to a general exponential family, a general smooth family, and also Markov sources. In particular, we show that variants of Jeffreys mixture asymptotically achieve their minimax values.

AB - We study the problem of data compression, gambling and prediction of a sequence xn = x1x2...xn from a certain alphabet X, in terms of regret (Shtarkov 1988) and redundancy with respect to a general exponential family, a general smooth family, and also Markov sources. In particular, we show that variants of Jeffreys mixture asymptotically achieve their minimax values.

UR - http://www.scopus.com/inward/record.url?scp=84890397548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890397548&partnerID=8YFLogxK

U2 - 10.1109/ISIT.1998.708923

DO - 10.1109/ISIT.1998.708923

M3 - Conference contribution

AN - SCOPUS:84890397548

SN - 0780350006

SN - 9780780350007

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 318

BT - Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998

T2 - 1998 IEEE International Symposium on Information Theory, ISIT 1998

Y2 - 16 August 1998 through 21 August 1998

ER -

Asymptotically minimax regret by bayes mixtures

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this