HKUST Library Institutional Repository Banner

HKUST Institutional Repository >
Computer Science and Engineering >
CSE Conference Papers >

Please use this identifier to cite or link to this item:
Title: Coherence functions for multicategory margin-based classification methods
Authors: Zhang, Zhihua
Jordan, Michael I.
Li, Wu-Jun
Yeung, Dit-Yan
Keywords: Classification methods
Coherence functions
Intractable minimization problem
Issue Date: Apr-2009
Citation: Proceedings of the 12th International Conference on Artificial Intelligence and Statistics (AISTATS) 2009, Clearwater Beach, Florida, USA, 16-18 April 2009, v. 5, p. 647-654
Abstract: Margin-based classification methods are typically devised based on a majorization-minimization procedure, which approximately solves an otherwise intractable minimization problem defined with the 0-l loss. The extension of such methods from the binary classification setting to the more general multicategory setting turns out to be non-trivial. In this paper, our focus is to devise margin-based classification methods that can be seamlessly applied to both settings, with the binary setting simply as a special case. In particular, we propose a new majorization loss function that we call the coherence function, and then devise a new multicategory margin-based boosting algorithm based on the coherence function. Analogous to deterministic annealing, the coherence function is characterized by a temperature factor. It is closely related to the multinomial log-likelihood function and its limit at zero temperature corresponds to a multicategory hinge loss function.
Rights: Reprinted with permission from MIT Press
Appears in Collections:CSE Conference Papers

Files in This Item:

File Description SizeFormat
coher.pdf517KbAdobe PDFView/Open

All items in this Repository are protected by copyright, with all rights reserved.