Elastic Net Gradient Vector

Problem

The elastic net penalty combines L1 and L2: lambda1 * ||w||_1 + (lambda2 / 2) * ||w||^2, whose gradient adds lambda1 * sign(w) + lambda2 * w.

Given the data gradient, the weights, lambda1, and lambda2, return the penalized gradient.

Hint

Combine both penalty gradients term by term.

case 1

in: [[1,2],[1,1],0.1,0.2]

expected: [1.3,2.3000000000000003]

case 2

in: [[0,0],[-1,0],0.5,0.5]

expected: [-1,0]

case 3

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

expected: [3]

Starter codePython

def elastic_net_gradient_vector(grad, weights, lambda1, lambda2):
    # Your code here
    pass

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