skglm.experimental.SqrtLasso

class skglm.experimental.SqrtLasso(alpha=1.0, max_iter=100, max_pn_iter=100, p0=10, tol=0.0001, verbose=0)

Square root Lasso estimator based on Prox Newton solver.

The optimization objective for square root Lasso is:

`||y - Xw||_2 + alpha ||w||_1`

Parameters:

alphafloat, default 1

Penalty strength.

max_iterint, default 20

Maximum number of outer iterations.

max_pn_iterint, default 1000

Maximum number of prox Newton iterations on each subproblem.

p0int, default 10

Minimum number of features to be included in the working set.

tolfloat, default 1e-4

Tolerance for convergence.

verbosebool, default False

Amount of verbosity. 0/False is silent.

__init__(alpha=1.0, max_iter=100, max_pn_iter=100, p0=10, tol=0.0001, verbose=0)

Methods

__init__([alpha, max_iter, max_pn_iter, p0, ...])
fit(X, y)	Fit the model according to the given training data.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
path(X, y[, alphas, eps, n_alphas])	Compute Lasso path.
predict(X)	Predict using the linear model.
score(X, y[, sample_weight])	Return the coefficient of determination of the prediction.
set_params(**params)	Set the parameters of this estimator.
set_score_request(*[, sample_weight])	Request metadata passed to the score method.