We consider a kind of support vector machines regression (SVMR) algorithms associated with coefficient-based regularization and data-dependent hypothesis space. Compared with former literature, we provide here a simpler convergence analysis for those algorithms. The novelty of our analysis lies in the estimation of the hypothesis error, which is implemented by setting a stepping stone between the coefficient regularized SVMR and the classical SVMR. An explicit learning rate is then derived under very mild conditions.
"A Simpler Approach to Coefficient Regularized Support Vector Machines Regression." Abstr. Appl. Anal. 2014 1 - 8, 2014. https://doi.org/10.1155/2014/206015