Author(s)

Pablo Rivas-Perea, Juan Cota-Ruiz, David Garcia Chaparro, Jorge Arturo Perez Venzor, Abel Quezada Carreón, Jose Gerardo Rosiles

Department of Computer Science, School of Engineering & Computer Science, Baylor University, Waco, USA.
Department of Electrical & Computer Engineering, Autonomous University of Ciudad Juárez, Ciudad Juárez, México.
Rosiles Consulting, El Paso, USA.

Support Vector-based learning methods are an important part of Computational Intelligence techniques. Recent efforts have been dealing with the problem of learning from very large datasets. This paper reviews the most commonly used formulations of support vector machines for regression (SVRs) aiming to emphasize its usability on large-scale applications. We review the general concept of support vector machines (SVMs), address the state-of-the-art on training methods SVMs, and explain the fundamental principle of SVRs. The most common learning methods for SVRs are introduced and linear programming-based SVR formulations are explained emphasizing its suitability for large-scale learning. Finally, this paper also discusses some open problems and current trends.

Support Vector Machines; Support Vector Regression; Linear Programming Support Vector Regression

P. Rivas-Perea, J. Cota-Ruiz, D. Chaparro, J. Venzor, A. Carreón and J. Rosiles, "Support Vector Machines for Regression: A Succinct Review of Large-Scale and Linear Programming Formulations," International Journal of Intelligence Science, Vol. 3 No. 1, 2013, pp. 5-14. doi: 10.4236/ijis.2013.31002.