sparseSVM-package {sparseSVM} | R Documentation |
Fast algorithm for fitting solution paths for sparse SVM regularized by lasso or elastic-net that generate sparse solutions.
Package: | sparseSVM |
Type: | Package |
Version: | 1.1-6 |
Date: | 2018-06-01 |
License: | GPL-3 |
Accepts X,y
data for binary classification and
produces the solution path over a grid of values of the regularization parameter lambda
. Also provides functions for plotting, prediction and parallelized cross-validation.
Congrui Yi and Yaohui Zeng
Maintainer: Congrui Yi <eric.ycr@gmail.com>
Yi, C. and Huang, J. (2017)
Semismooth Newton Coordinate Descent Algorithm for
Elastic-Net Penalized Huber Loss Regression and Quantile Regression,
https://www.tandfonline.com/doi/abs/10.1080/10618600.2016.1256816?journalCode=ucgs20
Journal of Computational and Graphical Statistics
X = matrix(rnorm(1000*100), 1000, 100) b = 3 w = 5*rnorm(10) eps = rnorm(1000) y = sign(b + drop(X[,1:10] %*% w + eps)) fit = sparseSVM(X, y) coef(fit, 0.05) predict(fit, X[1:5,], lambda = c(0.2, 0.1)) plot(fit) cv.fit <- cv.sparseSVM(X, y, ncores = 2, seed = 1234) predict(cv.fit, X) coef(cv.fit) plot(cv.fit)