Strong Asymptotic Assertions for Discrete MDL in Regression and Classification. Poland, J. & Hutter, M. In Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn-2005), Enschede, 2005.
Strong Asymptotic Assertions for Discrete MDL in Regression and Classification [link]Paper  bibtex   
@InProceedings{Poland:05mdlreg,
  author =       "J. Poland and M. Hutter",
  title =        "Strong Asymptotic Assertions for Discrete {MDL} in Regression and Classification",
  booktitle =    "Annual Machine Learning Conference of Belgium and the Netherlands ({Benelearn-2005})",
  address =      "Enschede",
  _editor =       "Martijn van Otterlo and Mannes Poel and Anton Nijholt",
  year =         "2005",
  http =         "http://www.hutter1.de/ai/mdlreg.htm",
  url =          "http://arxiv.org/abs/math.ST/0502315",
  ftp =          "http://www.idsia.ch/idsiareport/IDSIA-02-05.pdf",
  keywords =     "Regression, Classification, Sequence Prediction,
                  Machine Learning, Minimum Description Length, Bayes Mixture,
                  Marginalization, Convergence, Discrete Model Classes.",
}

Downloads: 0