DMCA
A greedy algorithm for optimizing the kernel alignment and the performance of kernel machines
| Venue: | In Proc. EUSIPCO ’06 |
| Citations: | 3 - 1 self |
BibTeX
@INPROCEEDINGS{Pothin_agreedy,
author = {Jean-baptiste Pothin and Cédric Richard},
title = {A greedy algorithm for optimizing the kernel alignment and the performance of kernel machines},
booktitle = {In Proc. EUSIPCO ’06},
year = {},
pages = {4--8}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Kernel-target alignment has recently been proposed as a criterion for measuring the degree of agreement between a reproducing kernel and a learning task. It makes possible to find a powerful kernel for a given classification problem without designing any classifier. In this paper, we present an alternating optimization strategy, based on a greedy algorithm for maximizing the alignment over linear combinations of kernels, and a gradient descent to adjust the free parameters of each kernel. Experimental results show an improvement in the classification performance of support vector machines, and a drastic reduction in the training time. 1.
Keyphrases
greedy algorithm kernel alignment kernel machine drastic reduction support vector machine training time reproducing kernel powerful kernel linear combination classification performance free parameter gradient descent classification problem alternating optimization strategy learning task experimental result kernel-target alignment
