skglm.datafits.QuadraticSVC

class skglm.datafits.QuadraticSVC[source]

A Quadratic SVC datafit used for classification tasks.

The datafit reads:

`1/2 ||(yX)^T w||_2 ^ 2`

Notes

The class is jit compiled at fit time using Numba compiler. This allows for faster computations.

__init__()[source]

Methods

__init__()

full_grad_sparse(yXT_data, yXT_indptr, ...)

get_global_lipschitz(yXT, y)

get_global_lipschitz_sparse(yXT_data, ...)

get_lipschitz(yXT, y)

get_lipschitz_sparse(yXT_data, yXT_indptr, ...)

get_spec()

Specify the numba types of the class attributes.

gradient_scalar(yXT, y, w, yXTw, j)

gradient_scalar_sparse(yXT_data, yXT_indptr, ...)

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.

params_to_dict()

Get the parameters to initialize an instance of the class.

value(y, w, yXTw)

Value of datafit at vector w.