Making Archetypal Analysis Practical

  • Christian Bauckhage
  • Christian Thurau
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5748)

Abstract

Archetypal analysis represents the members of a set of multivariate data as a convex combination of extremal points of the data. It allows for dimensionality reduction and clustering and is particularly useful whenever the data are superpositions of basic entities. However, since its computation costs grow quadratically with the number of data points, the original algorithm hardly applies to modern pattern recognition or data mining settings. In this paper, we introduce ways of notably accelerating archetypal analysis. Our experiments are the first successful application of the technique to large scale data analysis problems.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cutler, A., Breiman, L.: Archetypal Analysis. Technometrics 36(4), 338–347 (1994)MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Jolliffe, I.: Principal Component Analysis. Springer, Heidelberg (1986)CrossRefMATHGoogle Scholar
  3. 3.
    Schölkopf, B., Smola, A.J., Müller, K.-R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10(5), 1299–1319 (1998)CrossRefGoogle Scholar
  4. 4.
    Lee, D.D., Seung, S.: Learning the Parts of Objects by Non-Negative Matrix Factorization. Nature 401(6755), 788 (1999)CrossRefGoogle Scholar
  5. 5.
    Finesso, L., Spreij, P.: Approximate Nonnegative Matrix Factorization via Alternating Minimization. In: Proc. 16th Int. Symp. on Mathematical Theory of Networks and Systems, Leuven (July 2004)Google Scholar
  6. 6.
    Stone, E., Cutler, A.: Archetypal Analysis of Spatio-temporal Dynamics. Physica D 90(3), 209–224 (1996)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Chan, B.H.P.: Archetypal Analysis of Galaxy Spectra. Monthly Notices of the Royal Astronomical Society 338(3), 790–795 (2003)CrossRefGoogle Scholar
  8. 8.
    Huggins, P., Pachter, L., Sturmfels, B.: Toward the Human Genotope. Bulletin of Mathematical Biology 69(8), 2723–2735 (2007)MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    Joachims, T.: Making Large-Scale Support Vector Machine Learningn Practical. In: Advances in Kernel Methods: Support Vector Learning, MIT Press, Cambridge (1999)Google Scholar
  10. 10.
    de Berg, M., van Kreveld, M., Overmars, M., Schwarzkopf, O.: Computational Geometry. Springer, Heidelberg (2000)CrossRefMATHGoogle Scholar
  11. 11.
    Ziegler, G.M.: Lectures on Polytopes. Springer, Heidelberg (1995)CrossRefMATHGoogle Scholar
  12. 12.
    Donoho, D.L., Tanner, J.: Neighborliness of Randomly-Projected Simplices in High Dimensions. Proc. of the Nat. Academy of Sciences 102(27), 9452–9457 (2005)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Hall, P., Marron, J., Neeman, A.: Geometric representation of high dimension low sample size data. J. of the Royal Statistical Society B 67(3), 427–444 (2005)MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-Time Shapes. In: Proc. ICCV (2005)Google Scholar
  15. 15.
    Torralba, A., Fergus, R., Freeman, W.T.: 80 Million Tiny Images: A Large Dataset for Non-parametric Object and Scene Recognition. IEEE Trans. on Pattern Analalysis and Machine Intelligence 30(11), 1958–1970 (2008)CrossRefGoogle Scholar
  16. 16.
    Heidemann, G.: The principal components of natural images revisited. IEEE Trans. on Pattern Analalysis and Machine Intelligence 28(5), 822–826 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Christian Bauckhage
    • 1
    • 2
  • Christian Thurau
    • 1
  1. 1.Fraunhofer IAISSankt AugustinGermany
  2. 2.B-ITUniversity of BonnBonnGermany

Personalised recommendations