Jensen-Shannon Divergence

Problem

Compute the Jensen-Shannon divergence in bits between p and q:

m = (p + q) / 2 JSD = 0.5 * D(p || m) + 0.5 * D(q || m)

where D is the KL divergence in bits. Skip zero probability terms.

Hint

JSD is symmetric and bounded by 1 bit.

case 1

in: [[0.5,0.5],[0.5,0.5]]

expected: 0

case 2

in: [[1,0],[0,1]]

expected: 1

case 3

in: [[0.5,0.5],[0.25,0.75]]

expected: 0.0487949406953985

case 4

in: [[0.9,0.1],[0.5,0.5]]

expected: 0.1467931024360521

Starter codePython

import math
def jensen_shannon(p, q):
    # Your code here
    pass

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