PowerSumRegularizer

class PowerSumRegularizer(*, weight=1.0, apply_only_once=False, dim=-1, normalize=False, p=2.0, **kwargs)[source]

Bases: Regularizer

A simple x^p based regularizer.

Has some nice properties, cf. e.g. https://github.com/pytorch/pytorch/issues/28119.

Initialize the regularizer.

Parameters:
  • weight (float) – The relative weight of the regularization

  • apply_only_once (bool) – Should the regularization be applied more than once after reset?

  • dim (Optional[int]) – the dimension along which to calculate the Lp norm, cf. powersum_norm()

  • normalize (bool) – whether to normalize the norm by the dimension, cf. powersum_norm()

  • p (float) – the parameter \(p\) of the Lp norm, cf. powersum_norm()

  • kwargs – additional keyword-based parameters passed to Regularizer.__init__()

Methods Summary

forward(x)

Compute the regularization term for one tensor.

Methods Documentation

forward(x)[source]

Compute the regularization term for one tensor.

Return type:

FloatTensor

Parameters:

x (FloatTensor) –