An Estimate of the Misclassification Error with Hinge and Square Loss

In this paper we study how Tikhonov regularization can be effectively used in the context of learning theory, especially in support vector machine classification problems. We review formulations of classification problems in the context of ill-posed inverse problem and regularization. The main mathematical result of the paper is a new probabilistic bound for the support vector machine classification problem, where we use the Hinge loss (or soft margin loss function) and the square loss function.