glinternet: Learning Interactions via Hierarchical Group-Lasso Regularization

Group-Lasso INTERaction-NET. Fits linear pairwise-interaction models that satisfy strong hierarchy: if an interaction coefficient is estimated to be nonzero, then its two associated main effects also have nonzero estimated coefficients. Accommodates categorical variables (factors) with arbitrary numbers of levels, continuous variables, and combinations thereof. Implements the machinery described in the paper "Learning interactions via hierarchical group-lasso regularization" (JCGS 2015, Volume 24, Issue 3). Michael Lim & Trevor Hastie (2015) <DOI:10.1080/10618600.2014.938812>.

Getting started

Package details

AuthorMichael Lim, Trevor Hastie
MaintainerMichael Lim <michael626@gmail.com>
LicenseGPL-2
Version1.0.12
URL http://web.stanford.edu/~hastie/Papers/glinternet_jcgs.pdf
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:
install.packages("glinternet")

Try the glinternet package in your browser

Any scripts or data that you put into this service are public.

glinternet documentation built on Sept. 5, 2021, 5:28 p.m.