OrthogonalityRegularizer
- class OrthogonalityRegularizer(*, weight=1.0, apply_only_once=True, epsilon=1e-05, **kwargs)[source]
Bases:
Regularizer
A regularizer for the soft orthogonality constraints from [wang2014].
Initialize the regularizer.
- Parameters:
weight (
float
) – The relative weight of the regularizationapply_only_once (
bool
) – Should the regularization be applied more than once after reset?epsilon (
float
) – a small value used to check for approximate orthogonalitykwargs – additional keyword-based parameters passed to
Regularizer.__init__()
Attributes Summary
The default strategy for optimizing the TransH regularizer's hyper-parameters
Methods Summary
forward
(x)Compute the regularization term for one tensor.
update
(*tensors)Update the regularization term based on passed tensors.
Attributes Documentation
- hpo_default: ClassVar[Mapping[str, Any]] = {'weight': {'high': 1.0, 'low': 0.01, 'scale': 'log', 'type': <class 'float'>}}
The default strategy for optimizing the TransH regularizer’s hyper-parameters
Methods Documentation