See this document in CiteSeerX!

A constrained version of Sauer's Lemma (2004)  (Make Corrections)  (2 citations)
Joel Ratsaby



  Home/Search   Context   Related

 
View or download:
cs.ucl.ac.uk/staff/J.Rat...RN0313.pdf
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  cs.ucl.ac.uk/staff/J.Ratsaby/P... (more)
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: We generalize Sauer's Lemma to finite V C-dimension classes functions on [n] = . . . , n} which have a margin of at least N on every element in a sample S [n] of cardinality l, where the margin h (x) of h on a point [n] is defined as the largest non-negative integer a such that h is constant on the interval I a (x) = [x a, x + a]. (Update)

Cited by:   More
Complexity of VC-classes of sequences with long repetitive - Runs Joel Ratsaby   (Correct)
On the Complexity of Good Samples for Learning - Joel Ratsaby Department   (Correct)

Active bibliography (related documents):   More   All
0.0:   Complexity of Constrained VC-Classes - Joel Ratsaby Ben   (Correct)
0.0:   Discrete Mathematics and Theoretical Computer Science DMTCS.. - Bernard Ycart And   (Correct)
0.0:   A Constrained Version of Sauer's Lemma - Ratsaby (2004)   (Correct)

Similar documents based on text:   More   All
0.3:   On Learning Multicategory Classification with Sample Queries - Ratsaby (2003)   (Correct)
0.2:   A Stochastic Gradient Descent Algorithm for Structural Risk.. - Ratsaby (2003)   (Correct)
0.2:   A Sharp Threshold Result for VC-Classes of Large-Margin Functions .. - Ratsaby (2004)   (Correct)

Related documents from co-citation:   More   All
2:   Statistical Learning Theory (context) - Vapnik
2:   the uniform convergence of relative frequencies of events to their probabilities (context) - Vapnik, Chervonenkis - 1971
2:   Neural Network Learning: Theoretical Foundations (context) - Anthony, Bartlett - 1999

BibTeX entry:   (Update)

J. Ratsaby. A constrained version of sauer's lemma. In Third Colloquium on Mathematics and Computer Science Algorithms, Trees, Combinatorics and Probabilities, Vienna, Austria, September 2004 (MathInfo 2004), Proceedings. Birkhuser, 2004. http://citeseer.ist.psu.edu/ratsaby04constrained.html   More

@misc{ ratsaby04constrained,
  author = "J. Ratsaby",
  title = "A constrained version of sauer's lemma",
  text = "J. Ratsaby. A constrained version of sauer's lemma. In Third Colloquium
    on Mathematics and Computer Science Algorithms, Trees, Combinatorics and
    Probabilities, Vienna, Austria, September 2004 (MathInfo 2004), Proceedings.
    Birkhuser, 2004.",
  year = "2004",
  url = "citeseer.ist.psu.edu/ratsaby04constrained.html" }
Citations (may not include all citations):
947   Statistical Learning Theory (context) - Vapnik - 1998
454   the uniform convergence of relative frequencies of events to.. (context) - Vapnik, Chervonenkis - 1971
143   An Introduction to Support Vector Machines and other Kernel-.. (context) - Cristianini, Shawe-Taylor - 2000
115   the density of families of sets (context) - Sauer - 1972
114   The Theory of Partitions (context) - Andrews - 1998
88   Neural Network Learning:Theoretical Foundations (context) - Anthony, Bartlett - 1999
21   A generalization of Sauer's Lemma (context) - Haussler, Long - 1995
2   A Sharp Threshold Result for Finite-VC Classes of Large-Marg.. (context) - Ratsaby - 2004

Documents on the same site (http://www.cs.ucl.ac.uk/staff/J.Ratsaby/Publications/PDF/):   More
On the Learnability of Rich Function Classes - Ratsaby, Maiorov (1983)   (Correct)
Learning From A Mixture Of Labeled And Unlabeled Examples.. - Joel Ratsaby And (1995)   (Correct)
Towards Robust Model Selection using Estimation and - Approximation Error Bounds   (Correct)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC