skglm.experimental.SqrtQuadratic#

class skglm.experimental.SqrtQuadratic[source]#

Unnormalized square root quadratic datafit.

The datafit reads:

`||y - Xw||_2`
__init__()[source]#

Methods

__init__()

get_spec()

Specify the numba types of the class attributes.

initialize(X, y)

Pre-computations before fitting on X and y.

initialize_sparse(X_data, X_indptr, X_indices, y)

Pre-computations before fitting on X and y when X is a sparse matrix.

inverse_link(Xw)

Inverse link function (identity by default).

params_to_dict()

Get the parameters to initialize an instance of the class.

prox(w, step, y)

Prox of ``step * ||y - .

prox_conjugate(z, step, y)

Prox of ``step * ||y - .

raw_grad(y, Xw)

Compute gradient of datafit w.r.t Xw.

raw_hessian(y, Xw)

Diagonal matrix upper bounding the Hessian.

subdiff_distance(Xw, z, y)

Distance of z to subdiff of ||y - .

value(y, w, Xw)

Value of datafit at vector w.