Piecewise constant prediction

Erik Ordentlich, Marcelo J. Weinberger, Yihong Wu

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

Abstract

Minimax prediction of binary sequences is investigated for cases in which the predictor is forced to issue a piecewise constant prediction. The minimax strategy is characterized for Hamming loss whereas, for logarithmic loss, an asymptotically minimax strategy which achieves the leading term of the asymptotic minimax redundancy, is proposed. The average redundancy case is also analyzed for i.i.d. distributions. The piecewise constant prediction paradigm may be of relevance to resource constrained settings.

Original languageEnglish (US)
Title of host publication2012 IEEE International Symposium on Information Theory Proceedings, ISIT 2012
Pages880-884
Number of pages5
DOIs
StatePublished - Oct 22 2012
Event2012 IEEE International Symposium on Information Theory, ISIT 2012 - Cambridge, MA, United States
Duration: Jul 1 2012Jul 6 2012

Publication series

NameIEEE International Symposium on Information Theory - Proceedings

Other

Other2012 IEEE International Symposium on Information Theory, ISIT 2012
CountryUnited States
CityCambridge, MA
Period7/1/127/6/12

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Piecewise constant prediction'. Together they form a unique fingerprint.

  • Cite this

    Ordentlich, E., Weinberger, M. J., & Wu, Y. (2012). Piecewise constant prediction. In 2012 IEEE International Symposium on Information Theory Proceedings, ISIT 2012 (pp. 880-884). [6284688] (IEEE International Symposium on Information Theory - Proceedings). https://doi.org/10.1109/ISIT.2012.6284688