Asymptotically minimax regret by bayes mixtures

J. Takeuchi, A. R. Barron

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

22 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998
Number of pages1
DOIs
Publication statusPublished - Dec 1 1998
Externally publishedYes
Event1998 IEEE International Symposium on Information Theory, ISIT 1998 - Cambridge, MA, United States
Duration: Aug 16 1998Aug 21 1998

Publication series

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

Other

Other1998 IEEE International Symposium on Information Theory, ISIT 1998
CountryUnited States
CityCambridge, MA
Period8/16/988/21/98

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Asymptotically minimax regret by bayes mixtures'. Together they form a unique fingerprint.

Cite this