Understanding Stepwise Generalization of Support Vector Machines: A Toy Model

Abstract

In this article we study the effects of introducing structure in the input distribution of the data to be learnt by a simple perceptron. We determine the learning curves within the framework of Statis(cid:173) tical Mechanics. Stepwise generalization occurs as a function of the number of examples when the distribution of patterns is highly anisotropic. Although extremely simple, the model seems to cap(cid:173) ture the relevant features of a class of Support Vector Machines which was recently shown to present this behavior.

Cite

Text

Risau-Gusman and Gordon. "Understanding Stepwise Generalization of Support Vector Machines: A Toy Model." Neural Information Processing Systems, 1999.

Markdown

[Risau-Gusman and Gordon. "Understanding Stepwise Generalization of Support Vector Machines: A Toy Model." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/risaugusman1999neurips-understanding/)

BibTeX

@inproceedings{risaugusman1999neurips-understanding,
  title     = {{Understanding Stepwise Generalization of Support Vector Machines: A Toy Model}},
  author    = {Risau-Gusman, Sebastian and Gordon, Mirta B.},
  booktitle = {Neural Information Processing Systems},
  year      = {1999},
  pages     = {321-327},
  url       = {https://mlanthology.org/neurips/1999/risaugusman1999neurips-understanding/}
}