Massive Data Classification via Unconstrained Support Vector Machines

dc.contributor.author	Thompson, Michael
dc.contributor.author	Mangasarian, Olvi
dc.date.accessioned	2013-01-17T18:05:53Z
dc.date.available	2013-01-17T18:05:53Z
dc.date.issued	2006
dc.identifier.citation	06-01	en
dc.identifier.uri	http://digital.library.wisc.edu/1793/64336
dc.description.abstract	A highly accurate algorithm, based on support vector machines formulated as linear programs [13, 1], is proposed here as a completely unconstrained minimization problem [15]. Combined with a chunking procedure [2] this approach, which requires nothing more complex than a linear equation solver, leads to a simple and accurate method for classifying million-point datasets. Because a 1-norm support vector machine underlies the proposed approach, the method suppresses input space features as well. A state-of-the-art linear programming package, CPLEX [10], fails to solve problems handled by the proposed algorithm.	en
dc.subject	linear program	en
dc.subject	massive data classification	en
dc.subject	support vector machines	en
dc.title	Massive Data Classification via Unconstrained Support Vector Machines	en
dc.type	Technical Report	en

DMI Technical Reports
DMI Technical Reports Archive for the Department of Computer Sciences at the University of Wisconsin-Madison