Lookahead Interpolation

Problem

Perform one Lookahead interpolation step.

Given fast weights, slow weights, and alpha, compute slow_new = slow + alpha * (fast - slow) elementwise, and set fast_new = slow_new. Return [slow_new, fast_new] as two lists.

Hint

Fast weights snap back to the interpolated slow weights after the update.

Test cases

case 1

in: [[2,4],[1,1],0.5]

expected: [[1.5,2.5],[1.5,2.5]]

case 2

in: [[0,0],[2,-2],0.25]

expected: [[1.5,-1.5],[1.5,-1.5]]

case 3

in: [[1,2,3],[1,2,3],0.9]

expected: [[1,2,3],[1,2,3]]

Starter codePython

def lookahead_interpolate(fast, slow, alpha):
    # Returns [slow_new, fast_new]
    # Your code here
    pass

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