gflasso: Graph-guided fused Lasso via Smoothed Proximal Gradient...

In krisrs1128/gflasso: Perform graph structured multitask regression, according to Chen, et al.

Graph-guided fused Lasso via Smoothed Proximal Gradient Descent

Usage

gflasso(Y, X, R, opts = list())

Arguments

Y	The matrix of regression responses, scaled and centered as necessary.
X	The data matrix, scaled and centered as necessary.
R	The matrix of (thresholded) correlations between columns of Y
opts	A potentially partially specified list of regularization and gradient descent parameters. See merge_proxgrad_opts().

Value

A list containing the following quantities:
$B The estimated beta coefficient matrix. Its rows correspond columns of X, while its columns correspond to columns of Y.
$obj The graph fused lasso objective function, over iterations. $Lu The automatically calculated step size.
reference.

References

Smoothing Proximal Gradient Method for General Structured Sparse Regression

krisrs1128/gflasso documentation built on Nov. 11, 2023, 4:24 a.m.