def test_multinomial_grad_hess():
rng = np.random.RandomState(0)
n_samples, n_features, n_classes = 100, 5, 3
X = rng.randn(n_samples, n_features)
w = rng.rand(n_classes, n_features)
Y = np.zeros((n_samples, n_classes))
ind = np.argmax(np.dot(X, w.T), axis=1)
Y[range(0, n_samples), ind] = 1
w = w.ravel()
sample_weights = np.ones(X.shape[0])
grad, hessp = _multinomial_grad_hess(w,
X,
Y,
alpha=1.,
sample_weight=sample_weights)
# extract first column of hessian matrix
vec = np.zeros(n_features * n_classes)
vec[0] = 1
hess_col = hessp(vec)
# Estimate hessian using least squares as done in
# test_logistic_grad_hess
e = 1e-3
d_x = np.linspace(-e, e, 30)
d_grad = np.array([
_multinomial_grad_hess(w + t * vec,
X,
Y,
alpha=1.,
sample_weight=sample_weights)[0] for t in d_x
])
d_grad -= d_grad.mean(axis=0)
approx_hess_col = linalg.lstsq(d_x[:, np.newaxis], d_grad)[0].ravel()
assert_array_almost_equal(hess_col, approx_hess_col)
def test_multinomial_grad_hess():
rng = np.random.RandomState(0)
n_samples, n_features, n_classes = 100, 5, 3
X = rng.randn(n_samples, n_features)
w = rng.rand(n_classes, n_features)
Y = np.zeros((n_samples, n_classes))
ind = np.argmax(np.dot(X, w.T), axis=1)
Y[range(0, n_samples), ind] = 1
w = w.ravel()
sample_weights = np.ones(X.shape[0])
grad, hessp = _multinomial_grad_hess(w, X, Y, alpha=1.,
sample_weight=sample_weights)
# extract first column of hessian matrix
vec = np.zeros(n_features * n_classes)
vec[0] = 1
hess_col = hessp(vec)
# Estimate hessian using least squares as done in
# test_logistic_grad_hess
e = 1e-3
d_x = np.linspace(-e, e, 30)
d_grad = np.array([
_multinomial_grad_hess(w + t * vec, X, Y, alpha=1.,
sample_weight=sample_weights)[0]
for t in d_x
])
d_grad -= d_grad.mean(axis=0)
approx_hess_col = linalg.lstsq(d_x[:, np.newaxis], d_grad)[0].ravel()
assert_array_almost_equal(hess_col, approx_hess_col)
def _hessvec_fun_mult(w, v, X, y, sample_weight=None, reg_param=0): temp = _multinomial_grad_hess(w, X, y, reg_param, sample_weight)[1] return temp(v)
