Lesson 13 of 21 · Part IV, SVMs and ensembles

Support Vector Machines

Maximum margin and support vectors, the quadratic problem (primal and dual), soft margin and slack variables, kernels and the kernel trick, SVMs for regression with the ε-insensitive loss.

9 figures to manipulate.

In this lesson

• Part I — SVM for binary classification
• Soft margin SVM: allowing errors
• Kernels: SVM for nonlinear problems
• Part II — SVM for nonlinear regression

Other lessons

Statistical Learning Theory and VC-dimension · SVMs and kernels — practical aspects and a critical view · All lessons

Notes by Fabio Piscitelli — Machine Learning (654AA), Prof. Alessio Micheli, University of Pisa, a.y. 2026/27.