A meta-learning method to select the kernel width in Support Vector Regression

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F04%3A00010093" target="_blank" >RIV/00216224:14330/04:00010093 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

A meta-learning method to select the kernel width in Support Vector Regression

Original language description

The Support Vector Machine algorithm is sensitive to the choice of parameter settings. If these are not set correctly, the algorithm may have a substandard performance. Suggesting a good setting is thus an important problem. We propose a meta-learning methodology for this purpose and exploit information about the past performance of different settings. The methodology is applied to set the width of the Gaussian kernel. We carry out an extensive empirical evaluation, including comparisons with other methods (fixed default ranking; selection based on cross-validation and a heuristic method commonly used to set the width of the SVM kernel). We show that our methodology can select settings with low error while providing significant savings in time. Furtherwork should be carried out to see how the methodology could be adapted to different parameter setting tasks.

Czech name

Metoda meta-učení pro volbu šířky jádra

Czech description

The Support Vector Machine algorithm is sensitive to the choice of parameter settings. If these are not set correctly, the algorithm may have a substandard performance. Suggesting a good setting is thus an important problem. We propose a meta-learning methodology for this purpose and exploit information about the past performance of different settings. The methodology is applied to set the width of the Gaussian kernel. We carry out an extensive empirical evaluation, including comparisons with other methods (fixed default ranking; selection based on cross-validation and a heuristic method commonly used to set the width of the SVM kernel). We show that our methodology can select settings with low error while providing significant savings in time. Furtherwork should be carried out to see how the methodology could be adapted to different parameter setting tasks.

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2004

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Machine Learning Journal

ISSN

0885-6125

e-ISSN

—

Volume of the periodical

54

Issue of the periodical within the volume

3

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

15

Pages from-to

195-209

UT code for WoS article

—

EID of the result in the Scopus database

—