Several decades ago, Support Vector Machines (SVMs) were introduced for performing binary classification tasks, under a supervised framework. Nowadays, they often outperform other supervised methods and remain one of the most popular
approaches in the machine learning arena. In this work, we investigate the training
of SVMs through a smooth sparse-promoting-regularized squared hinge loss minimization. This choice paves the way for the application of quick training methods
built on majorization-minimization approaches, benefiting from the Lipschitz differentiability of the loss function. Moreover, the proposed approach allows us to handle
sparsity-preserving regularizers promoting the selection of the most significant features, so enhancing the performance. Numerical tests and comparisons conducted on three different datasets demonstrate the good performance of the proposed methodology in terms of qualitative metrics (accuracy, precision, recall, and F1 score) as well as computational cost.
