ML Anthology

Projection Support Vector Machine Generators

Francisco J. González-Castaño, Ubaldo M. García-Palomares, Robert R. Meyer
MLJ 2004 pp. 33-44
doi:10.1023/B:MACH.0000008083.47006.86 /mlj/2004/gonzalezcastano2004mlj-projection/

Abstract

Large-scale Support Vector Machine (SVM) classification is a very active research line in data mining. In recent years, several efficient SVM generation algorithms based on quadratic problems have been proposed, including: Successive OverRelaxation (SOR), Active Support Vector Machines (ASVM) and Lagrangian Support Vector Machines (LSVM). These algorithms have been used to solve classification problems with millions of points. ASVM is perhaps the fastest among them. This paper compares a new projection-based SVM algorithm with ASVM on a selection of real and synthetic data sets. The new algorithm seems competitive in terms of speed and testing accuracy.

PDF MLJ Semantic Scholar

Cite

Text

González-Castaño et al. "Projection Support Vector Machine Generators." Machine Learning, 2004. doi:10.1023/B:MACH.0000008083.47006.86

Markdown

[González-Castaño et al. "Projection Support Vector Machine Generators." Machine Learning, 2004.](https://mlanthology.org/mlj/2004/gonzalezcastano2004mlj-projection/) doi:10.1023/B:MACH.0000008083.47006.86

BibTeX

@article{gonzalezcastano2004mlj-projection,
  title     = {{Projection Support Vector Machine Generators}},
  author    = {González-Castaño, Francisco J. and García-Palomares, Ubaldo M. and Meyer, Robert R.},
  journal   = {Machine Learning},
  year      = {2004},
  pages     = {33-44},
  doi       = {10.1023/B:MACH.0000008083.47006.86},
  volume    = {54},
  url       = {https://mlanthology.org/mlj/2004/gonzalezcastano2004mlj-projection/}
}