lasso.net.fixed {LassoNet} | R Documentation |
Estimates coefficients over the grid values of penalty parameters.
Description
See lasso.net.grid
Usage
lasso.net.fixed(x,y,beta.0,lambda1,lambda2,M1,n.iter,iscpp,tol)
Arguments
x |
|
y |
response vector or size |
beta.0 |
initial value for |
lambda1 |
lasso penalty coefficient |
lambda2 |
network penalty coefficient |
M1 |
penalty matrix |
n.iter |
maximum number of iterations for |
iscpp |
binary choice for using cpp function in coordinate updates; 1 - use C++ (default), 0 - use R. |
tol |
convergence in |
Details
Function loops through the grid of values of penalty parameters 1 and
2 until convergence is reached. Warm starts are stored for each iterator. The warm starts are stored once the coordinate updating converges.
Value
beta |
Matrix of |
mse |
Mean squared error value |
iterations |
matrix with stored number of steps for sign matrix to converge |
update.steps |
matrix with stored number of steps for |
convergence.in.grid |
matrix with stored values for convergence in |
Author(s)
Maintainer: Jonas Striaukas <jonas.striaukas@gmail.com>
References
Weber, M., Striaukas, J., Schumacher, M., Binder, H. "Network-Constrained Covariate Coefficient and Connection Sign Estimation" (2018) <doi:10.2139/ssrn.3211163>
Examples
p=200
n=100
beta.0=array(1,c(p,1))
x=matrix(rnorm(n*p),n,p)
y=rnorm(n,mean=0,sd=1)
lambda1=c(0,1)
lambda2=c(0,1)
M1=diag(p)
lasso.net.fixed(x, y, beta.0, lambda1, lambda2, M1)