Partial linearization based optimization for multi-class SVM

Conference item

We propose a novel partial linearization based approach for optimizing the multi-class svm learning problem. Our method is an intuitive generalization of the Frank-Wolfe and the exponentiated gradient algorithms. In particular, it allows us to combine several of their desirable qualities into one approach: (i) the use of an expectation oracle (which provides the marginals over each output class) in order to estimate an informative descent direction, similar to exponentiated gradient; (ii) analytical computation of the optimal step-size in the descent direction that guarantees an increase in the dual objective, similar to Frank-Wolfe; and (iii) a block coordinate formulation similar to the one proposed for Frank-Wolfe, which allows us to solve large-scale problems. Using the challenging computer vision problems of action classification, object recognition and gesture recognition, we demonstrate the efficacy of our approach on training multi-class svms with standard, publicly available, machine learning datasets.

Authors: Mohapatra, P; Dokania, P; Jawahar, C; Kumar, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer International Publishing
• Host title: Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V
• Series: Lecture Notes in Computer Science
• Publication date: 2016-01-01
• Acceptance date: 2016-07-11
• DOI: 10.1007/978-3-319-46454-1_51
• EISSN: 1611-3349
• ISSN: 0302-9743
• ISBN: 9783319464534
• Keywords: partial linearization; optimization; multi-class svm