Defines a cooling schedule following a geometric sequence.
tfp.experimental.sequential.geometric_cooling_schedule(
cooling_fraction_per_k_iterations, k=1.0
)
This returns a function f
such that
f(iteration) = cooling_fraction_per_k_iterations**(iteration / k)
Args |
cooling_fraction_per_k_iterations
|
float Tensor ratio by which the
original value should be scaled once k iterations have been completed.
|
k
|
int Tensor number of iterations used to define the schedule.
|
Returns |
f
|
Python callable representing the cooling schedule.
|