PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Constrained version of Sauer's Lemma
Joel Ratsaby
In: Algorithms, Trees, Combinatorics and Probabilities (2004) Birkhausser Verlag , pp. 543-551. ISBN 0817671285

Abstract

Sauer's Lemma is extended to classes $\mH$ of binary-valued functions on $[n]=\{1, \ldots, n\}$ which have a margin less than or equal to $N$ on $x\in[n]$, where the margin $\mu_h(x)$ of a binary valued function $h$ at a point $x\in [n]$ is defined as the largest non-negative integer $a$ such that $h$ is constant on the interval $I_a(x) =[x-a, x+a] \subseteq [n]$. Estimates are obtained for the cardinality of classes of binary valued functions with a margin of at least $N$ on a sample $S\subseteq[n]$.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Additional Information:Future updated versions of this work are at http://www.bgu.ac.il/~ratsaby/Publications.htm
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:804
Deposited By:Joel Ratsaby
Deposited On:30 December 2004