Linear Algebraic proofs of VC-Dimension based inequalities

  • Leonid Gurvits
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1208)


We apply linear algebra(polynomial) techniques to various VC-Dimension based inequalities. We explore connections between the sample compression and this technique for so called maximum classes and prove that maximum classes are connected subgraphs of a Boolean cube.We provide a fast (linear in the cardinality of the class for the fixed VC-dimension) interpolational algorithm for maximum classes.A new method to bound a pseudo-dimension for a class of cell-wise constant functions is proposed.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [BF92]
    L.Babai and P.Frankl. Linear algebra methods in combinatorics with applications to geometry and computer science. (Preliminary Version 2), 1992, Dept. of Computer Science,The University of Chicago.Google Scholar
  2. [FrWi81]
    P.Frankl and R.M.Wilson. Intersection theorems with geometric consequences. Combinatorica 1(1981),357–368.Google Scholar
  3. [FW95]
    S.Floyd and M.Warmuth. Sample compression,learnability,and the Vapnik-Chervonenkis dimension, Machine Learning, 1–36, 1995.Google Scholar
  4. [We]
    E. Welzl.(1987). Complete range spaces.Unpublished notes.Google Scholar
  5. [HL]
    D.Haussler and Phil Long.(1991) A generalization of Sauer's lemma, UCSC-CRL-90-15.Google Scholar
  6. [GJ93]
    P.Goldberg and M.Jerrum (1993). Bounding the Vapnik-Chervonenkis dimension of concepts classes parameterized by real numbers. In proc. 6th Annual ACM Conference on Computational Learning Theory.Google Scholar
  7. [Sa72]
    N.Sauer (1972). On the density of families of sets. J. Comb. Theory, Series A 13(1972), 145–147.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Leonid Gurvits
    • 1
    • 2
  1. 1.NEC Research InstitutePrinceton
  2. 2.DIMACSRutgers UniversityNew Brunswick

Personalised recommendations