Title :
Tight bounds for SVM classification error
Author :
Apolloni, B. ; Bassis, S. ; Gaito, S. ; Malchiodi, D.
Author_Institution :
Dipartimento di Sci. dell´´Informazione, Universita degli Studi di Milano, Milan
Abstract :
We find very tight bounds on the accuracy of a support vector machine classification error within the algorithmic inference framework. The framework is specially suitable for this kind of classifier since (i) we know the number of support vectors really employed, as an ancillary output of the learning procedure, and (ii) we can appreciate confidence intervals of misclassifying probability exactly in function of the cardinality of these vectors. As a result we obtain confidence intervals that are up to an order narrower than those supplied in the literature, having a slight different meaning due to the different approach they come from, but the same operational function. We numerically check the covering of these intervals
Keywords :
learning (artificial intelligence); pattern classification; support vector machines; algorithmic inference framework; ancillary output; confidence intervals; learning procedure; support vector machine classification error; Constraint optimization; Electronic mail; Equations; Error probability; Inference algorithms; Machine learning; Machine learning algorithms; Support vector machine classification; Support vector machines; Upper bound;
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
DOI :
10.1109/ICNNB.2005.1614556
