Bias-Variance Decomposition

Problem

Return the expected squared error at a point from its information decomposition:

E[(y - f_hat)^2] = bias^2 + variance + noise

where noise is the irreducible error of the data-generating process.

Hint

Only the bias and variance terms are under the modeler's control.

case 1

in: [1,1,1]

expected: 3

case 2

in: [0,0,0]

expected: 0

case 3

in: [0.5,0.25,0.25]

expected: 0.75

case 4

in: [2,3,0]

expected: 7

Starter codePython

def bias_variance_decomposition(bias, variance, noise):
    # Your code here
    pass

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