PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Gaps in Support Vector Optimization
Nikolas List, Don Hush, Clint Scovel and Ingo Steinwart
In: COLT 2007, 13-15 June 2007, San Diego, California.

Abstract

We show that the stopping criteria used in many support vector machine (SVM) algorithms working on the dual can be interpreted as primal optimality bounds which in turn are known to be important for the statistical analysis of SVMs. To this end we revisit the duality theory underlying the derivation of the dual and show that in many interesting cases primal optimality bounds are the same as known dual optimality bounds.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:2987
Deposited By:Nikolas List
Deposited On:23 April 2007