From Separating to Proximal Plane Classifiers: A Review
A review of parallel and proximal plane classifiers is proposed. We discuss separating plane classifier introduced in support vector machines and we describe different proposals to obtain two proximal planes representing the two classes in the binary classification case. In details, we deal with proximal SVM classification by means of a generalized eigenvalues problem. Furthermore, some regularization techniques are analyzed in order to solve the singularity of the matrices. For the same purpose, proximal support vector machine using local information is handled. In addition, a brief description of twin support vector machines and nonparallel plane proximal classifier is reported.
KeywordsSupport vector machine Proximal plane classifier Regularized generalized eigenvalue classifier
Authors would like to thank Dr. Panos Pardalos for the fruitful discussions and advice. This work has been partially funded by Italian Flagship project Interomics and by the Italian Ministry of Education, University and Research grant PON_00619.
- 2.Vapnik, V.: Estimation of Dependences Based on Empirical Data [in Russian]. Nauka, Moscow (1979). (English translation: Springer, New York, 1982)Google Scholar
- 3.Pardalos, P.M., Hansen, P. (eds.): Data Mining and Mathematical Programming. CRM Proceedings and Lecture Notes, American Mathematical Society. vol. 45 (2008)Google Scholar
- 5.Fung, G., Mangasarian, O.L.: Proximal support vector machine classifiers. In: Proceedings KDD-2001: Knowledge Discovery and Data Mining (KDD 2001), San Francisco, CA (2001)Google Scholar
- 9.Jayadeva, Khemchandani, R., Chandra, S.: Twin Support Vector Machines for Pattern Classification. IEEE Trans. Pattern Anal. Mach. Intell. 29, 905 (2007)Google Scholar
- 13.Mangasarian, O.L.: Least norm solution of non-monotone complementarity problems. In: Functional Analysis, Optimization and Mathematical Economics, pp. 217–221. New York, Oxford University Press (1990)Google Scholar