Linear MMD

Problem

Compute the squared maximum mean discrepancy with a linear kernel: the squared Euclidean distance between the sample means.

Return 0.0 if either sample is empty.

Hint

Linear MMD only compares first moments, so mean shifts dominate.

case 1

in: [[[0,0],[1,1]],[[2,2],[3,4]]]

expected: 10.25

case 2

in: [[[1],[2]],[[4],[5]]]

expected: 9

case 3

in: [[[0,0]],[[0,0]]]

expected: 0

case 4

in: [[],[]]

expected: 0

Starter codePython

def linear_mmd(x, y):
    # Your code here
    pass

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