When Is Small Beautiful?

  • Amiran Ambroladze
  • John Shawe-Taylor
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2777)


The basic bound on the generalisation error of a PAC learner makes the assumption that a consistent hypothesis exists. This makes it appropriate to apply the method only in the case where we have a guarantee that a consistent hypothesis can be found, something that is rarely possible in real applications. The same problem arises if we decide not to use a hypothesis unless its error is below a prespecified number.


  1. 1.
    Shave-Taylor, J., Anthony, M., Biggs, N.L.: Bounding Sample Size with the Vapnik-Chervonenkis Dimension. Discrete Applied Maths 42, 65–73 (1993)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Amiran Ambroladze
    • 1
  • John Shawe-Taylor
    • 2
  1. 1.Lunds UniversityLund
  2. 2.Department of Computer ScienceRoyal HollowayEngland

Personalised recommendations