Feature Selection via L1-Penalized Squared-Loss Mutual Information
Machine Learning
2015-06-11 v1 Machine Learning
Abstract
Feature selection is a technique to screen out less important features. Many existing supervised feature selection algorithms use redundancy and relevancy as the main criteria to select features. However, feature interaction, potentially a key characteristic in real-world problems, has not received much attention. As an attempt to take feature interaction into account, we propose L1-LSMI, an L1-regularization based algorithm that maximizes a squared-loss variant of mutual information between selected features and outputs. Numerical results show that L1-LSMI performs well in handling redundancy, detecting non-linear dependency, and considering feature interaction.
Cite
@article{arxiv.1210.1960,
title = {Feature Selection via L1-Penalized Squared-Loss Mutual Information},
author = {Wittawat Jitkrittum and Hirotaka Hachiya and Masashi Sugiyama},
journal= {arXiv preprint arXiv:1210.1960},
year = {2015}
}
Comments
25 pages