Learning Curve Gap

Problem

Compute the gap between validation and training error at each learning-curve size: val_error - train_error element-wise.

Empty input returns [].

Hint

A shrinking positive gap suggests the model is starting to generalize.

case 1

in: [[0.5,0.3,0.2],[0.6,0.5,0.45]]

expected: [0.09999999999999998,0.2,0.25]

case 2

in: [[1,2],[1,2]]

expected: [0,0]

case 3

in: [[0.9],[0.1]]

expected: [-0.8]

case 4

in: [[],[]]

expected: []

Starter codePython

def learning_curve_gap(train_errors, val_errors):
    # Your code here
    pass

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