## A second-order perceptron algorithm (2005)

### Cached

### Download Links

- [eprints.pascal-network.org]
- [homes.di.unimi.it]
- [www.dicom.uninsubria.it]
- [mercurio.srv.di.unimi.it]
- [cispa.crema.unimi.it]
- DBLP

### Other Repositories/Bibliography

Citations: | 59 - 21 self |

### BibTeX

@MISC{Cesa-Bianchi05asecond-order,

author = {Nicolò Cesa-Bianchi and Alex Conconi and Claudio Gentile},

title = {A second-order perceptron algorithm},

year = {2005}

}

### Years of Citing Articles

### OpenURL

### Abstract

Kernel-based linear-threshold algorithms, such as support vector machines and Perceptron-like algorithms, are among the best available techniques for solving pattern classification problems. In this paper, we describe an extension of the classical Perceptron algorithm, called second-order Perceptron, and analyze its performance within the mistake bound model of on-line learning. The bound achieved by our algorithm depends on the sensitivity to second-order data information and is the best known mistake bound for (efficient) kernel-based linear-threshold classifiers to date. This mistake bound, which strictly generalizes the well-known Perceptron bound, is expressed in terms of the eigenvalues of the empirical data correlation matrix and depends on a parameter controlling the sensitivity of the algorithm to the distribution of these eigenvalues. Since the optimal setting of this parameter is not known a priori, we also analyze two variants of the second-order Perceptron algorithm: one that adaptively sets the value of the parameter in terms of the number of mistakes made so far, and one that is parameterless, based on pseudoinverses.