DMCA
Hierarchical penalization (2007)
Cached
Download Links
| Venue: | IN ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 20 |
| Citations: | 15 - 3 self |
BibTeX
@INPROCEEDINGS{Szafranski07hierarchicalpenalization,
author = {Marie Szafranski and Yves Grandvalet and Pierre Morizet-mahoudeaux},
title = {Hierarchical penalization},
booktitle = {IN ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 20},
year = {2007},
publisher = {MIT press}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Hierarchical penalization is a generic framework for incorporating prior information in the fitting of statistical models, when the explicative variables are organized in a hierarchical structure. The penalizer is a convex functional that performs soft selection at the group level, and shrinks variables within each group. This favors solutions with few leading terms in the final combination. The framework, originally derived for taking prior knowledge into account, is shown to be useful in linear regression, when several parameters are used to model the influence of one feature, or in kernel regression, for learning multiple kernels.
Keyphrases
hierarchical penalization several parameter kernel regression final combination linear regression shrink variable soft selection explicative variable favor solution group level generic framework multiple kernel hierarchical structure prior information convex functional statistical model prior knowledge
