bound_upper_sharp

bound_upper_sharp(param: Tensor, update: Tensor, limit: float, **kwargs) → Tensor

Computes the scaled update of upper-bound sharp parameter dependence.

This is sometimes also referred to as “hard parameter dependence”.

\[U_+ = \Theta(P_\text{max} - P) U_+\]

Where

\[\begin{split}\Theta(x) = \begin{cases} 1 &x \geq 0 \\ 0 & x < 0 \end{cases}\end{split}\]

Parameters:

• param (torch.Tensor) – parameter with update bounding, \(P\).

• update (torch.Tensor) – potentiative update being applied, \(U_+\).

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

Returns:

bounded update.

Return type:

torch.Tensor