PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On the smallest possible dimension and the largest possible margin of linear arrangements representing given concept classes
Juergen Forster and Hans Simon
Theoretical Computer Science Volume 350, Number 1, pp. 40-48, 2006.

Abstract

This paper discusses theoretical limitations of classification systems that are based on feature maps and use a separating hyperplane in the feature space. In particular, we study the embeddability of a given concept class into a class of Euclidean half spaces of low dimension, or of arbitrarily large dimension but realizing a large margin. New bounds on the smallest possible dimension or on the largest possible margin are presented. In addition, we present new results on the rigidity of matrices and briefly mention applications in complexity and learning theory.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:2215
Deposited By:Hans Simon
Deposited On:29 September 2006