Graph-Sparse Logistic Regression
Machine Learning
2017-12-18 v1 Machine Learning
Abstract
We introduce Graph-Sparse Logistic Regression, a new algorithm for classification for the case in which the support should be sparse but connected on a graph. We val- idate this algorithm against synthetic data and benchmark it against L1-regularized Logistic Regression. We then explore our technique in the bioinformatics context of proteomics data on the interactome graph. We make all our experimental code public and provide GSLR as an open source package.
Cite
@article{arxiv.1712.05510,
title = {Graph-Sparse Logistic Regression},
author = {Alexander LeNail and Ludwig Schmidt and Johnathan Li and Tobias Ehrenberger and Karen Sachs and Stefanie Jegelka and Ernest Fraenkel},
journal= {arXiv preprint arXiv:1712.05510},
year = {2017}
}
Comments
7 pages, 2 figures, NIPS DISCML workshop paper