secml.ml.classifiers.regularizer¶

CRegularizer¶

class secml.ml.classifiers.regularizer.c_regularizer.CRegularizer[source]¶

Bases: secml.core.c_creator.CCreator

Abstract class that defines basic methods for regularizer functions.

Attributes

class_type: Defines class type.
logger: Logger for current object.
verbose: Verbosity level of logger output.

Methods

`copy`(self)	Returns a shallow copy of current class.
`create`([class_item])	This method creates an instance of a class with given type.
`deepcopy`(self)	Returns a deep copy of current class.
`dregularizer`(self, args, *kwargs)	Gets the derivative of regularizer.
`get_class_from_type`(class_type)	Return the class associated with input type.
`get_params`(self)	Returns the dictionary of class hyperparameters.
`get_state`(self, **kwargs)	Returns the object state dictionary.
`get_subclasses`()	Get all the subclasses of the calling class.
`list_class_types`()	This method lists all types of available subclasses of calling one.
`load`(path)	Loads object from file.
`load_state`(self, path)	Sets the object state from file.
`regularizer`(self, args, *kwargs)	Gets value of regularizer.
`save`(self, path)	Save class object to file.
`save_state`(self, path, **kwargs)	Store the object state to file.
`set`(self, param_name, param_value[, copy])	Set a parameter of the class.
`set_params`(self, params_dict[, copy])	Set all parameters passed as a dictionary {key: value}.
`set_state`(self, state_dict[, copy])	Sets the object state using input dictionary.
`timed`([msg])	Timer decorator.

dregularizer(self, *args, **kwargs)[source]¶: Gets the derivative of regularizer.

abstract regularizer(self, *args, **kwargs)[source]¶: Gets value of regularizer.

CRegularizerElasticNet¶

class secml.ml.classifiers.regularizer.c_regularizer_elastic_net.CRegularizerElasticNet(l1_ratio=0.15)[source]¶

Bases: secml.ml.classifiers.regularizer.c_regularizer.CRegularizer

ElasticNet Regularizer.

A convex combination of L2 and L1, where $\rho$ is given by 1 - l1_ratio.

ElasticNet Regularizer is given by:

$R(w) := \frac{\rho}{2} \sum_{i=1}^{n} w_i^2 + (1-\rho) \sum_{i=1}^{n} |w_i|$

Attributes

class_type‘elastic-net’: Defines class type.

Methods

`copy`(self)	Returns a shallow copy of current class.
`create`([class_item])	This method creates an instance of a class with given type.
`deepcopy`(self)	Returns a deep copy of current class.
`dregularizer`(self, w)	Returns the derivative of the elastic-net regularizer
`get_class_from_type`(class_type)	Return the class associated with input type.
`get_params`(self)	Returns the dictionary of class hyperparameters.
`get_state`(self, **kwargs)	Returns the object state dictionary.
`get_subclasses`()	Get all the subclasses of the calling class.
`list_class_types`()	This method lists all types of available subclasses of calling one.
`load`(path)	Loads object from file.
`load_state`(self, path)	Sets the object state from file.
`regularizer`(self, w)	Returns ElasticNet Regularizer.
`save`(self, path)	Save class object to file.
`save_state`(self, path, **kwargs)	Store the object state to file.
`set`(self, param_name, param_value[, copy])	Set a parameter of the class.
`set_params`(self, params_dict[, copy])	Set all parameters passed as a dictionary {key: value}.
`set_state`(self, state_dict[, copy])	Sets the object state using input dictionary.
`timed`([msg])	Timer decorator.

dregularizer(self, w)[source]¶

Returns the derivative of the elastic-net regularizer

Parameters

wCArray: Vector-like array.

property l1_ratio¶: Get l1-ratio.

regularizer(self, w)[source]¶

Returns ElasticNet Regularizer.

Parameters

wCArray: Vector-like array.

CRegularizerL1¶

class secml.ml.classifiers.regularizer.c_regularizer_l1.CRegularizerL1[source]¶

Bases: secml.ml.classifiers.regularizer.c_regularizer.CRegularizer

Norm-L1 Regularizer.

This function leads to sparse solutions.

L1 Regularizer is given by:

$R(w) := \sum_{i=1}^{n} |w_i|$

Attributes

class_type‘l1’: Defines class type.

Methods

`copy`(self)	Returns a shallow copy of current class.
`create`([class_item])	This method creates an instance of a class with given type.
`deepcopy`(self)	Returns a deep copy of current class.
`dregularizer`(self, w)	Returns Norm-L1 derivative.
`get_class_from_type`(class_type)	Return the class associated with input type.
`get_params`(self)	Returns the dictionary of class hyperparameters.
`get_state`(self, **kwargs)	Returns the object state dictionary.
`get_subclasses`()	Get all the subclasses of the calling class.
`list_class_types`()	This method lists all types of available subclasses of calling one.
`load`(path)	Loads object from file.
`load_state`(self, path)	Sets the object state from file.
`regularizer`(self, w)	Returns Norm-L1.
`save`(self, path)	Save class object to file.
`save_state`(self, path, **kwargs)	Store the object state to file.
`set`(self, param_name, param_value[, copy])	Set a parameter of the class.
`set_params`(self, params_dict[, copy])	Set all parameters passed as a dictionary {key: value}.
`set_state`(self, state_dict[, copy])	Sets the object state using input dictionary.
`timed`([msg])	Timer decorator.

dregularizer(self, w)[source]¶

Returns Norm-L1 derivative.

Parameters

wCArray: Vector-like array.

regularizer(self, w)[source]¶

Returns Norm-L1.

Parameters

wCArray: Vector-like array.

CRegularizerL2¶

class secml.ml.classifiers.regularizer.c_regularizer_l2.CRegularizerL2[source]¶

Bases: secml.ml.classifiers.regularizer.c_regularizer.CRegularizer

Norm-L2 Regularizer.

L2 Regularizer is given by:

$R(w) := \frac {1}{2} \sum_{i=1}^{n} w_i^2$

Attributes

class_type‘l2’: Defines class type.

Methods

`copy`(self)	Returns a shallow copy of current class.
`create`([class_item])	This method creates an instance of a class with given type.
`deepcopy`(self)	Returns a deep copy of current class.
`dregularizer`(self, w)	Return Norm-L2 derivative.
`get_class_from_type`(class_type)	Return the class associated with input type.
`get_params`(self)	Returns the dictionary of class hyperparameters.
`get_state`(self, **kwargs)	Returns the object state dictionary.
`get_subclasses`()	Get all the subclasses of the calling class.
`list_class_types`()	This method lists all types of available subclasses of calling one.
`load`(path)	Loads object from file.
`load_state`(self, path)	Sets the object state from file.
`regularizer`(self, w)	Returns Norm-L2.
`save`(self, path)	Save class object to file.
`save_state`(self, path, **kwargs)	Store the object state to file.
`set`(self, param_name, param_value[, copy])	Set a parameter of the class.
`set_params`(self, params_dict[, copy])	Set all parameters passed as a dictionary {key: value}.
`set_state`(self, state_dict[, copy])	Sets the object state using input dictionary.
`timed`([msg])	Timer decorator.

dregularizer(self, w)[source]¶

Return Norm-L2 derivative.

Parameters

wCArray: Vector-like array.

regularizer(self, w)[source]¶

Returns Norm-L2.

Parameters

wCArray: Vector-like array.