Inverse Time Decay Schedule

Problem

The inverse time decay schedule is lr_t = lr0 / (1 + k * t).

Given the base rate lr0, the decay rate k, and the step t, return the learning rate.

Hint

The denominator grows linearly with the step count.

case 1

in: [0.1,0.01,100]

expected: 0.05

case 2

in: [1,1,0]

expected: 1

case 3

in: [0.5,0.5,3]

expected: 0.2

Starter codePython

def inverse_time_decay_schedule(lr0, k, t):
    # Your code here
    pass

3 test cases · run your code against them in the editor