Support Vector Machines: Optimization Based Theory, Algorithms, and Extensions

Enabling a sound understanding of SVMs, this book gives readers the tools to solve real-world problems using SVMs. It presents an accessible treatment of the two main components of SVMs-classification problems and regression problems. The authors emphasize the close connection between optimization theory and SVMs since optimization is one of the pillars on which SVMs are built. They construct SVMs for semi-supervised, knowledge-based, and robust classification problems. They also cover SVMs for Universum, privileged, multi-class, multi-instance, and multi-label classification problems.