Поиск минимума функции с scipy.optimize.minimize

Прошу помочь с исправлением ошибки. Код оптимизации следующий:

import numpy as np
from scipy.optimize import Bounds, minimize
m = 20
n = 10
np.random.seed(1)
X = np.random.randn(m, n)
y = np.random.randn(m)
bounds = Bounds(np.zeros([n]), np.ones([n]))
def f_1(theta):
    return (np.dot(X,theta) - y)**2
theta = np.random.randn(n)
x0 = np.random.randn(n)
minimize(f_1, x0=x0, bounds=bounds)

Получаю ошибку:

ValueError                                Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/scipy/optimize/optimize.py in _approx_fprime_helper(xk, f, epsilon, args, f0)
    699             try:
--> 700                 df = df.item()
    701             except (ValueError, AttributeError):

ValueError: can only convert an array of size 1 to a Python scalar

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
4 frames
/usr/local/lib/python3.6/dist-packages/scipy/optimize/optimize.py in _approx_fprime_helper(xk, f, epsilon, args, f0)
    700                 df = df.item()
    701             except (ValueError, AttributeError):
--> 702                 raise ValueError("The user-provided "
    703                                  "objective function must "
    704                                  "return a scalar value.")

ValueError: The user-provided objective function must return a scalar value.

Не понимаю, что именно не нравится интерпретатору?