Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

January 2007, Vol. 19, No. 1, Pages 258-282
(doi: 10.1162/neco.2007.19.1.258)
© 2006 Massachusetts Institute of Technology
Second-Order Cone Programming Formulations for Robust Multiclass Classification
Article PDF (155.04 KB)
Abstract

Multiclass classification is an important and ongoing research subject in machine learning. Current support vector methods for multiclass classification implicitly assume that the parameters in the optimization problems are known exactly. However, in practice, the parameters have perturbations since they are estimated from the training data, which are usually subject to measurement noise. In this article, we propose linear and nonlinear robust formulations for multiclass classification based on the M-SVM method. The preliminary numerical experiments confirm the robustness of the proposed method.