• DocumentCode
    2001217
  • Title

    On closures of exponential families and their subfamilies

  • Author

    Csiszár, I. ; Matús, F.

  • Author_Institution
    A. Renyi Inst. of Math., Hungarian Acad. of Sci., Budapest, Hungary
  • fYear
    2003
  • fDate
    29 June-4 July 2003
  • Firstpage
    55
  • Abstract
    The variation distance closures of exponential families and their log-convex subfamilies are characterized. A problem left open in (I. Csiszar, et al., 2002) is settled: an exponential family is constructed whose closure in reversed information divergence, rI-closure, is neither rI-closed nor log-convex.
  • Keywords
    exponential distribution; information theory; maximum likelihood estimation; exponential families; log-convex subfamily; rI-closure; reversed information divergence; variation distance closure; Automation; Content addressable storage; Density measurement; Entropy; Mathematics; Measurement standards;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Theory, 2003. Proceedings. IEEE International Symposium on
  • Print_ISBN
    0-7803-7728-1
  • Type

    conf

  • DOI
    10.1109/ISIT.2003.1228069
  • Filename
    1228069