nemos.regularizer.UnRegularized#

class nemos.regularizer.UnRegularized[source]#

Bases: Regularizer

Regularizer class for unregularized models.

This class equips models with the identity proximal operator (no shrinkage) and the unpenalized loss function.

Attributes

allowed_solvers

default_solver

__init__()[source]#

Methods

__init__()

get_params([deep])

From scikit-learn, get parameters by inspecting init.

get_proximal_operator()

Returns the identity operator.

penalized_loss(loss, regularizer_strength)

Returns the original loss function unpenalized.

set_params(**params)

Set the parameters of this estimator.
property allowed_solvers: Tuple[str]#
property default_solver: str#
get_params(deep=True)#

From scikit-learn, get parameters by inspecting init.

Parameters:

deep

Return type:

dict

Returns:

out:

A dictionary containing the parameters. Key is the parameter name, value is the parameter value.

get_proximal_operator()[source]#

Returns the identity operator.

Unregularized method corresponds to an identity proximal operator, since no shrinkage factor is applied.

Return type:

Callable[[Any, float, float], Tuple[Array, Array]]

penalized_loss(loss, regularizer_strength)[source]#

Returns the original loss function unpenalized.

Unregularized regularization method does not add any penalty.

Parameters:

  • loss (Callable)

  • regularizer_strength (float)

set_params(**params)#

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**params (dict) – Estimator parameters.

Returns:

self – Estimator instance.

Return type:

estimator instance