smoothedLasso (version 1.6)

minimizeFunction: Minimize the objective function of an unsmoothed or smoothed regression operator with respect to \(betavector\) using BFGS.

Description

Minimize the objective function of an unsmoothed or smoothed regression operator with respect to \(betavector\) using BFGS.

Usage

minimizeFunction(p, obj, objgrad)

Arguments

p

The dimension of the unknown parameters (regression coefficients).

obj

The objective function of the regression operator as a function of \(betavector\).

objgrad

The gradient function of the regression operator as a function of \(betavector\).

Value

The estimator \(betavector\) (minimizer) of the regression operator.

References

Hahn, G., Lutz, S., Laha, N., and Lange, C. (2020). A framework to efficiently smooth L1 penalties for linear regression. bioRxiv:2020.09.17.301788.

Examples

# NOT RUN {
library(smoothedLasso)
n <- 100
p <- 500
betavector <- runif(p)
X <- matrix(runif(n*p),nrow=n,ncol=p)
y <- X %*% betavector
lambda <- 1
temp <- standardLasso(X,y,lambda)
obj <- function(z) objFunctionSmooth(z,temp$u,temp$v,temp$w,mu=0.1)
objgrad <- function(z) objFunctionSmoothGradient(z,temp$w,temp$du,temp$dv,temp$dw,mu=0.1)
print(minimizeFunction(p,obj,objgrad))

# }