ALT 2012: Algorithmic Learning Theory pp 96-110 | Cite as

Sauer’s Bound for a Notion of Teaching Complexity

  • Rahim Samei
  • Pavel Semukhin
  • Boting Yang
  • Sandra Zilles
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7568)

Abstract

This paper establishes an upper bound on the size of a concept class with given recursive teaching dimension (RTD, a teaching complexity parameter.) The upper bound coincides with Sauer’s well-known bound on classes with a fixed VC-dimension. Our result thus supports the recently emerging conjecture that the combinatorics of VC-dimension and those of teaching complexity are intrinsically interlinked.

We further introduce and study RTD-maximum classes (whose size meets the upper bound) and RTD-maximal classes (whose RTD increases if a concept is added to them), showing similarities but also differences to the corresponding notions for VC-dimension.

Another contribution is a set of new results on maximal classes of a given VC-dimension.

Methodologically, our contribution is the successful application of algebraic techniques, which we use to obtain a purely algebraic characterization of teaching sets (sample sets that uniquely identify a concept in a given concept class) and to prove our analog of Sauer’s bound for RTD.

Keywords

VC-dimension teaching Sauer’s bound maximum classes 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Doliwa, T.: Personal communication (2011)Google Scholar
  2. 2.
    Doliwa, T., Simon, H.U., Zilles, S.: Recursive Teaching Dimension, Learning Complexity, and Maximum Classes. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds.) ALT 2010. LNCS, vol. 6331, pp. 209–223. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Floyd, S., Warmuth, M.K.: Sample compression, learnability, and the Vapnik-Chervonenkis dimension. Machine Learning 21(3), 269–304 (1995)Google Scholar
  4. 4.
    Goldman, S.A., Kearns, M.J.: On the complexity of teaching. Journal of Computer and System Sciences 50, 20–31 (1995)MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Kuzmin, D., Warmuth, M.K.: Unlabeled compression schemes for maximum classes. J. Mach. Learn. Res. 8, 2047–2081 (2007)MathSciNetMATHGoogle Scholar
  6. 6.
    Rubinstein, B.I.P., Bartlett, P.L., Rubinstein, J.H.: Shifting: One-inclusion mistake bounds and sample compression. J. Comput. Syst. Sci. 75(1), 37–59 (2009)MathSciNetMATHCrossRefGoogle Scholar
  7. 7.
    Sauer, N.: On the density of families of sets. J. Comb. Theory, Ser. A 13(1), 145–147 (1972)MathSciNetMATHCrossRefGoogle Scholar
  8. 8.
    Shelah, S.: A combinatorial problem: Stability and order for models and theories in infinitary languages. Pac. J. Math. 4, 247–261 (1972)Google Scholar
  9. 9.
    Shinohara, A., Miyano, S.: Teachability in computational learning. New Generation Comput. 8(4), 337–347 (1991)MATHCrossRefGoogle Scholar
  10. 10.
    Smolensky, R.: Well-known bound for the VC-dimension made easy. Computational Complexity 6(4), 299–300 (1997)MathSciNetMATHCrossRefGoogle Scholar
  11. 11.
    Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl. 16, 264–280 (1971)MATHCrossRefGoogle Scholar
  12. 12.
    Welzl, E.: Complete range spaces. Unpublished notes (1987)Google Scholar
  13. 13.
    Zilles, S., Lange, S., Holte, R., Zinkevich, M.: Models of cooperative teaching and learning. Journal of Machine Learning Research 12, 349–384 (2011)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Rahim Samei
    • 1
  • Pavel Semukhin
    • 1
  • Boting Yang
    • 1
  • Sandra Zilles
    • 1
  1. 1.Department of Computer ScienceUniversity of ReginaCanada

Personalised recommendations