PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Statistical performance of support vector machines
Pascal Massart, Gilles Blanchard and Olivier Bousquet
Tha Annals of Statistics 32, 2004.

Abstract

The Support Vector Machine algorithm is well known to the computer learning community for its very good practical results. The goal of this paper is to study this algorithm from a statistical perspective, using tools of concentration theory and empirical processes.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:633
Deposited By:Michele Sebag
Deposited On:29 December 2004