rankflasso: Computes the rank fused-Lasso regression estimates for given...

In Mufabo/Rrobustsp: Robust Signal Processing

Computes the rank fused-Lasso regression estimates for given fused penalty value lambda_2 and for a range of lambda_1 values

Description

Computes the rank fused-Lasso regression estimates for given fused penalty value lambda_2 and for a range of lambda_1 values

Usage

rankflasso(y, X, lambda1, lambda2, b0 = NULL, printitn = 0)

Arguments

y	: numeric response N x 1 vector (real/complex)
X	: numeric feature N x p matrix (real/complex)
lambda1	: positive penalty parameter for the Lasso penalty term
lambda2	: positive penalty parameter for the fused Lasso penalty term
b0	: numeric optional initial start (regression vector) of iterations. If not given, we use LSE (when p>1).
printitn	: print iteration number (default = 0, no printing)

Value

b : numeric regression coefficient vector

iter : positive integer, the number of iterations of IRWLS algorithm

Mufabo/Rrobustsp documentation built on June 11, 2022, 10:41 p.m.