Timezone: »

On higher-order perceptron algorithms
Claudio Gentile · Fabio Vitale · Cristian Brotto

Tue Dec 04 10:30 AM -- 10:40 AM (PST) @ None #None

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.

Author Information

Claudio Gentile (INRIA)
Fabio Vitale (University of Lille)
Cristian Brotto (DICOM, Universita dell' Insubria)

More from the Same Authors