Improved MDL Estimators Using Local Exponential Family Bundles Applied to Mixture Families

Kohei Miyamoto, Andrew R. Barron, Jun'ichi Takeuchi

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

抄録

The MDL estimators for density estimation, which are defined by two-part codes for universal coding, are analyzed. We give a two-part code for mixture families whose regret is close to the minimax regret, where regret of a code with respect to a target family is the difference between the codelength of the code and the ideal codelength achieved by an element in . Our code is constructed using a probability density in an enlarged family of (a bundle of local exponential families of ) for data description. This result gives a tight upper bound on the risk of the MDL estimator defined by the two-part code, based on the theory introduced by Barron and Cover in 1991.

本文言語英語
ホスト出版物のタイトル2019 IEEE International Symposium on Information Theory, ISIT 2019 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1442-1446
ページ数5
ISBN(電子版)9781538692912
DOI
出版ステータス出版済み - 7 2019
イベント2019 IEEE International Symposium on Information Theory, ISIT 2019 - Paris, フランス
継続期間: 7 7 20197 12 2019

出版物シリーズ

名前IEEE International Symposium on Information Theory - Proceedings
2019-July
ISSN(印刷版)2157-8095

会議

会議2019 IEEE International Symposium on Information Theory, ISIT 2019
Countryフランス
CityParis
Period7/7/197/12/19

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 「Improved MDL Estimators Using Local Exponential Family Bundles Applied to Mixture Families」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