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

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

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

Abstract

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.

Original languageEnglish
Title of host publication2019 IEEE International Symposium on Information Theory, ISIT 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1442-1446
Number of pages5
ISBN (Electronic)9781538692912
DOIs
Publication statusPublished - Jul 2019
Event2019 IEEE International Symposium on Information Theory, ISIT 2019 - Paris, France
Duration: Jul 7 2019Jul 12 2019

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2019-July
ISSN (Print)2157-8095

Conference

Conference2019 IEEE International Symposium on Information Theory, ISIT 2019
CountryFrance
CityParis
Period7/7/197/12/19

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Improved MDL Estimators Using Local Exponential Family Bundles Applied to Mixture Families'. Together they form a unique fingerprint.

Cite this