Asymptotically minimax regret for models with hidden variables

Junnichi Takeuchi, Andrew R. Barron

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

3 被引用数 (Scopus)

抄録

We study the problems of data compression, gambling and prediction of a string xn = x1x2...xn from an alphabet X, in terms of regret with respect to models with hidden variables including general mixture families. When the target class is a non-exponential family, a modification of Jeffreys prior which has measure outside the given family of densities was introduced to achieve the minimax regret [8], under certain regularity conditions. In this paper, we show that the models with hidden variables satisfy those regularity conditions, when the hidden variables' model is an exponential family. In paticular, we do not have to restrict the class of data strings so that the MLE is in the interior of the parameter space for the case of the general mixture family.

本文言語英語
ホスト出版物のタイトル2014 IEEE International Symposium on Information Theory, ISIT 2014
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3037-3041
ページ数5
ISBN(印刷版)9781479951864
DOI
出版ステータス出版済み - 1 1 2014
イベント2014 IEEE International Symposium on Information Theory, ISIT 2014 - Honolulu, HI, 米国
継続期間: 6 29 20147 4 2014

出版物シリーズ

名前IEEE International Symposium on Information Theory - Proceedings
ISSN(印刷版)2157-8095

その他

その他2014 IEEE International Symposium on Information Theory, ISIT 2014
Country米国
CityHonolulu, HI
Period6/29/147/4/14

All Science Journal Classification (ASJC) codes

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

フィンガープリント 「Asymptotically minimax regret for models with hidden variables」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル