bound_lower_scaled_multiplicative

bound_lower_scaled_multiplicative(param: Tensor, update: Tensor, limit: float, range: float, **kwargs) Tensor[source]

Computes the scaled update of lower-bound scaled multiplicative parameter dependence.

This is sometimes also referred to as “soft parameter dependence” and is equivalent to power dependence with an exponent of 1.

\[U_- = \left(\frac{P - P_\text{min}}{P_\text{max} - P_\text{min}}\right) U_-\]
Parameters:
  • param (torch.Tensor) – parameter with update bounding, \(P\).

  • update (torch.Tensor) – depressive update being applied, \(U_-\).

  • limit (float) – value of the upper bound, \(P_\text{min}\).

  • range (float) – absolute difference between the upper and lower bounds, \(P_\text{max} - P_\text{min}\).

Returns:

bounded update.

Return type:

torch.Tensor