bound_upper_scaled_multiplicative¶
- bound_upper_scaled_multiplicative(param: Tensor, update: Tensor, limit: float, range: float, **kwargs) Tensor[source]¶
Computes the scaled update of upper-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.
\[U_+ = \left(\frac{P_\text{max} - P}{P_\text{max} - P_\text{min}}\right) U_+\]- Parameters:
param (torch.Tensor) – parameter with update bounding, \(P\).
update (torch.Tensor) – potentiative update being applied, \(U_+\).
limit (float) – value of the upper bound, \(P_\text{max}\).
range (float) – absolute difference between the upper and lower bounds, \(P_\text{max} - P_\text{min}\).
- Returns:
bounded update.
- Return type: