def do_nesterov_accelerated_gradient_descent():
    w, b, eta = init_w, init_b, 1.0
    prev_v_w, prev_v_b, gamma = 0, 0, 0.9
    for i in range(max_epochs):
        dw, db = 0, 0
        # do partial update
        v_w = gamma * prev_v_w
        v_b = gamma * prev_v_b
        for x,y in zip(X,Y):
          # calculate gradients after partial update
            dw += grad_w(w, b, x, y)
            db += grad_b(w, b, x, y)
        # now do the full update
        v_w = gamma * prev_v_w + eta*dw
        v_b = gamma * prev_v_b + eta*db
        w = w - v_w
        b = b - v-b
        prev_v_w = v_w
        prev_v_b = v_b