Least square Support Vector Machine for large-scale dataset

Support Vector Machine (SVM) is a very well-known tool for classification and regression problems. Many applications require SVMs with non-linear kernels for accurate classification. Training time complexity for SVMs with non-linear kernels is typically quadratic in the size of the training dataset. In this paper, we depart from the very well-known variation of SVM, the so-called Least Square Support Vector Machine, and apply Steepest Sub-gradient Descent method to propose Steepest Sub-gradient Descent Least Square Support Vector Machine (SGD-LSSVM). It is theoretically proven that the convergent rate of the proposed method to gain ε - precision solution is O (log (1/ε)). The experiments established on the large-scale datasets indicate that the proposed method offers the comparable classification accuracies while being faster than the baselines.