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.
N. List, D. Hush, C. Scovel and I. Steinwart, Gaps in support vector optimization. In Proceedings of the 20th Conference on Learning Theory, 336-348, 2007. Los Alamos National Laboratory Technical Report LA-UR-07-0621. [ Abstract ]
