Algorithms for Constructing Min-Max Partitions of the Parameter Space for MDL Inference

  • Adriana Vasilache
  • Ioan Tăbuş
  • Jorma Rissanen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)

Abstract

In this paper we present several algorithms for the construction of min-max optimal partitions of the parameter space. Two interpretations of the problem lead to two families of practical algorithms that are tested and compared.

References

  1. 1.
    Rissanen, J., Tăbuş, I.: Kolmogorov’s structure function in MDL theory and lossy data compression. In: Advances in Minimum Description Length: Theory and Applications, MIT Press, Cambridge (2004)Google Scholar
  2. 2.
    Rissanen, J.: Lectures on statistical modeling theory. Lecture notes, Tampere University of Technology (2003) Google Scholar
  3. 3.
    Kay, S.M.: Fundamentals of Statistical Signal Processing: Estimation Theory. Prentice Hall International, Inc., Englewood Cliffs (1993)MATHGoogle Scholar
  4. 4.
    Li, J., Chaddha, N., Gray, R.M.: Asymptotic performance of vector quantizers with a perceptual distortion measure. IEEE Trans. on Information Theory 45, 1082–1091 (1999)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Sinkkonen, J., Kaski, S., Nikkilä, J.: Discriminative clustering: optimal contigency tables by learning metrics. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) Proceedings of the 13th European Conference on Machine Learning. LNCS (LNAI), pp. 418–430 (2002)Google Scholar
  6. 6.
    Kohonen, T.: Self organization and associative memory, 3rd edn. Springer, Berlin (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Adriana Vasilache
    • 1
  • Ioan Tăbuş
    • 1
  • Jorma Rissanen
    • 1
  1. 1.Tampere University of TechnologyTampereFinland

Personalised recommendations