ML Anthology

Non-Negative Matrix Factorization as a Feature Selection Tool for Maximum Margin Classifiers

Mithun Das Gupta, Jing Xiao
CVPR 2011 pp. 2841-2848
doi:10.1109/CVPR.2011.5995492 /cvpr/2011/gupta2011cvpr-non/

Abstract

Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition tool for multivariate data. Non-negative bases allow strictly additive combinations which have been shown to be part-based as well as relatively sparse. We pursue a discriminative decomposition by coupling NMF objective with a maximum margin classifier, specifically a support vector machine (SVM). Conversely, we propose an NMF based regularizer for SVM. We formulate the joint update equations and propose a new method which identifies the decomposition as well as the classification parameters. We present classification results on synthetic as well as real datasets.

PDF CVPR Semantic Scholar

Cite

Text

Das Gupta and Xiao. "Non-Negative Matrix Factorization as a Feature Selection Tool for Maximum Margin Classifiers." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995492

Markdown

[Das Gupta and Xiao. "Non-Negative Matrix Factorization as a Feature Selection Tool for Maximum Margin Classifiers." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/gupta2011cvpr-non/) doi:10.1109/CVPR.2011.5995492

BibTeX

@inproceedings{gupta2011cvpr-non,
  title     = {{Non-Negative Matrix Factorization as a Feature Selection Tool for Maximum Margin Classifiers}},
  author    = {Das Gupta, Mithun and Xiao, Jing},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2841-2848},
  doi       = {10.1109/CVPR.2011.5995492},
  url       = {https://mlanthology.org/cvpr/2011/gupta2011cvpr-non/}
}