A Note on the Generalization Performance of Kernel Classifiers with Margin

Abstract

We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the Vγ dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.

Cite

Text

Evgeniou and Pontil. "A Note on the Generalization Performance of Kernel Classifiers with Margin." International Conference on Algorithmic Learning Theory, 2000. doi:10.1007/3-540-40992-0_23

Markdown

[Evgeniou and Pontil. "A Note on the Generalization Performance of Kernel Classifiers with Margin." International Conference on Algorithmic Learning Theory, 2000.](https://mlanthology.org/alt/2000/evgeniou2000alt-note/) doi:10.1007/3-540-40992-0_23

BibTeX

@inproceedings{evgeniou2000alt-note,
  title     = {{A Note on the Generalization Performance of Kernel Classifiers with Margin}},
  author    = {Evgeniou, Theodoros and Pontil, Massimiliano},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2000},
  pages     = {306-315},
  doi       = {10.1007/3-540-40992-0_23},
  url       = {https://mlanthology.org/alt/2000/evgeniou2000alt-note/}
}