LASSO: Lasso Regression (c++)

Description Usage Arguments Details Value Author(s) References

Description

Computes the coefficient estimates for lasso-penalized linear regression.

Usage

1
2
LASSO(X, Y, lam = 0.1, crit = c("loss", "avg", "max"), tol = 1e-04,
  maxit = 10000)

Arguments

X

nxp data matrix.

Y

nxr matrix of response values

lam

tuning parameter for lasso regularization term. Defaults to lam = 0.1.

crit

criterion for convergence. Criterion loss will loop until the relative change in the objective for each response after an iteration is less than tol. Criterion avg will loop until the average absolute change for each response is less than tol times tolerance multiple. Similary, criterion max will loop until the maximum absolute change is less than tol times tolerance multiple. Defaults to loss.

tol

tolerance for algorithm convergence. Defaults to 1e-4..

maxit

maximum iterations. Defaults to 1e4

Details

For details on the implementation of 'GLASSO', see the vignette https:#mgallow.github.io/GLASSO/.

Value

returns list of returns which includes:

Call

function call.

Iterations

number of iterations.

Loss

value of the objective function.

Coefficients

estimated regression coefficients.

Author(s)

Matt Galloway gall0441@umn.edu

References


MGallow/GLASSOO documentation built on May 8, 2019, 3:13 a.m.