InverseScaling¶
Reduces the learning rate using a power schedule.
Assuming an initial learning rate \(\eta\), the learning rate at step \(t\) is:
\[\\frac{eta}{(t + 1) ^ p}\]
where \(p\) is a user-defined parameter.
Parameters¶
-
learning_rate
Type → float
-
power
Default →
0.5
Methods¶
get
Returns the learning rate at a given iteration.
Parameters
- t — 'int'