Record Details

Using Sequential Unconstrained Minimization Techniques to simplify SVM solvers

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Using Sequential Unconstrained Minimization Techniques to simplify SVM solvers
 
Creator JOSHI, S
JAYADEVA
RAMAKRISHNAN, G
CHANDRA, S
 
Subject Support vector machines
SVM
SMO
SUPPORT VECTOR MACHINES
SMO ALGORITHM
IMPROVEMENTS
 
Description In this paper, we apply Sequential Unconstrained Minimization Techniques (SUMTs) to the classical formulations of both the classical L1 norm SVM and the least squares SVM. We show that each can be solved as a sequence of unconstrained optimization problems with only box constraints. We propose relaxed SVM and relaxed LSSVM formulations that correspond to a single problem in the corresponding SUMT sequence. We also propose a SMO like algorithm to solve the relaxed formulations that works by updating individual Lagrange multipliers. The methods yield comparable or better results on large benchmark datasets than classical SVM and LSSVM formulations, at substantially higher speeds. (C) 2011 Elsevier B.V. All rights reserved.
 
Publisher ELSEVIER SCIENCE BV
 
Date 2014-10-16T12:22:05Z
2014-10-16T12:22:05Z
2012
 
Type Article
 
Identifier NEUROCOMPUTING, 77(1)253-260
http://dx.doi.org/10.1016/j.neucom.2011.07.010
http://dspace.library.iitb.ac.in/jspui/handle/100/15534
 
Language en