chainer.optimizer_hooks.Lasso

class chainer.optimizer_hooks.Lasso(rate)[source]

Optimizer/UpdateRule hook function for Lasso regularization.

This hook function adds a scaled parameter to the sign of each weight. It can be used as a regularization.

Parameters

rate (float) – Coefficient for the weight decay.

Variables
  • ~optimizer_hooks.Lasso.rate (float) – Coefficient for the weight decay.

  • ~optimizer_hooks.Lasso.timing (string) – Specifies when this hook should be called by the Optimizer/UpdateRule. Valid values are ‘pre’ (before any updates) and ‘post’ (after any updates).

  • ~optimizer_hooks.Lasso.call_for_each_param (bool) – Specifies if this hook is called for each parameter (True) or only once (False) by an optimizer to which this hook is registered. This function does not expect users to switch the value from default one, which is True.

New in version 4.0.0: The timing parameter.

Methods

__call__(rule, param)[source]

Call self as a function.

__eq__(value, /)

Return self==value.

__ne__(value, /)

Return self!=value.

__lt__(value, /)

Return self<value.

__le__(value, /)

Return self<=value.

__gt__(value, /)

Return self>value.

__ge__(value, /)

Return self>=value.

Attributes

call_for_each_param = True
name = 'Lasso'
timing = 'pre'