• DocumentCode
    2053834
  • Title

    Optimal Bregman prediction and Jensen´s equality

  • Author

    Banerjee, Arindam ; Guo, Xin ; Wang, Hui

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA
  • fYear
    2004
  • fDate
    27 June-2 July 2004
  • Firstpage
    169
  • Abstract
    This paper provides necessary and sufficient conditions for general loss functions under which the conditional expectation is the unique optimal predictor of a random variable. Further, using such loss functions, we give an exact characterization of the difference between the two sides of Jensen´s inequality.
  • Keywords
    optimisation; prediction theory; random processes; stochastic processes; Jensen´s inequality; optimal Bregman prediction; random variable; Euclidean distance; Least squares methods; Random variables; Sufficient conditions;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Theory, 2004. ISIT 2004. Proceedings. International Symposium on
  • Print_ISBN
    0-7803-8280-3
  • Type

    conf

  • DOI
    10.1109/ISIT.2004.1365205
  • Filename
    1365205