I'm looking for a Python package for a LS-SVM or a way to tune a normal SVM from scikit-learn to a Least-Squares Support Vector Machine for a classification problem.
The goal of a SVM is to maximize the margin while softly penalizing points that lie on the wrong side of the margin boundary. The function that is used is a Quadratic Programming (OP) problem.
A LS-SVM which defines a least squares cost function and replaces the inequality contraints with equality constraints and is a Linear Programming (LP) problem.
Does someone ever tried something like that and can help me?