On Higher-Order Perceptron Algorithms

Abstract

A new algorithm for on-line learning linear-threshold functions is proposed which efficiently combines second-order statistics about the data with the logarithmic behavior" of multiplicative/dual-norm algorithms. An initial theoretical analysis is provided suggesting that our algorithm might be viewed as a standard Perceptron algorithm operating on a transformed sequence of examples with improved margin properties. We also report on experiments carried out on datasets from diverse domains, with the goal of comparing to known Perceptron algorithms (first-order, second-order, additive, multiplicative). Our learning procedure seems to generalize quite well, and converges faster than the corresponding multiplicative baseline algorithms."

Cite

Text

Gentile et al. "On Higher-Order Perceptron Algorithms." Neural Information Processing Systems, 2007.

Markdown

[Gentile et al. "On Higher-Order Perceptron Algorithms." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/gentile2007neurips-higherorder/)

BibTeX

@inproceedings{gentile2007neurips-higherorder,
  title     = {{On Higher-Order Perceptron Algorithms}},
  author    = {Gentile, Claudio and Vitale, Fabio and Brotto, Cristian},
  booktitle = {Neural Information Processing Systems},
  year      = {2007},
  pages     = {521-528},
  url       = {https://mlanthology.org/neurips/2007/gentile2007neurips-higherorder/}
}