we will consider a deep linear network model, which involves solving the following optimization problem: min W1,W2,W3 1 2 k P(W3W2W1) P(M)k 2 F , (3) where each Wi R dd for all i = 1, 2, 3. Notice that there is no explicit rank constraint!Compute the gradients of Equation (3) with respect to W1 R dd , W2 R dd , and W3 R dd