Building Sparse Multiple-Kernel SVM Classifiers

The support vector machines (SVMs) have been very successful in many machine learning problems. However, they can be slow during testing because of the possibly large number of support vectors obtained. Recently, Wu (2005) proposed a sparse formulation that restricts the SVM to use a small number of...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2009-05, Vol.20 (5), p.827-839
Main Authors: Mingqing Hu, Yiqiang Chen, Kwok, J.T.-Y.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Classifiers
Computer science
control theory
systems
Data processing. List processing. Character string processing
Exact sciences and technology
Formulations
Gradient projection
Kernel
kernel methods
Kernels
Machine learning
Mathematical analysis
Memory organisation. Data processing
multiple-kernel learning (MKL)
Neural networks
Quadratic programming
Risk management
Software
Solvers
Space technology
sparsity
Statistical learning
Studies
support vector machine (SVM)
Support vector machine classification
Support vector machines
Testing
Vectors (mathematics)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The support vector machines (SVMs) have been very successful in many machine learning problems. However, they can be slow during testing because of the possibly large number of support vectors obtained. Recently, Wu (2005) proposed a sparse formulation that restricts the SVM to use a small number of expansion vectors. In this paper, we further extend this idea by integrating with techniques from multiple-kernel learning (MKL). The kernel function in this sparse SVM formulation no longer needs to be fixed but can be automatically learned as a linear combination of kernels. Two formulations of such sparse multiple-kernel classifiers are proposed. The first one is based on a convex combination of the given base kernels, while the second one uses a convex combination of the so-called ldquoequivalentrdquo kernels. Empirically, the second formulation is particularly competitive. Experiments on a large number of toy and real-world data sets show that the resultant classifier is compact and accurate, and can also be easily trained by simply alternating linear program and standard SVM solver.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/TNN.2009.2014229