def test_update_L_C_single_equals_compute_L_C_when_initialised_correctly():
sigma = 1.
lmbda = 2.
N = 200
D = 2
m = 10
X = np.random.randn(N, D)
# basis
omega, u = rff_sample_basis(D, m, sigma)
# initial fit and update
L_C_update = np.eye(m) * np.sqrt(lmbda)
n_update = m
for x in X:
L_C_update = update_L_C_single(x, L_C_update, n_update, omega, u)
n_update += 1
# initial fit and batch (average of "fake" b and new observations
L_C_fake = np.eye(m) * np.sqrt(lmbda)
n_fake = m
C_batch = (np.dot(L_C_fake, L_C_fake.T) * n_fake +
compute_C(X, omega, u) * N) / (n_fake + N)
L_C_batch = np.linalg.cholesky(C_batch)
assert_allclose(L_C_update, L_C_batch)
def __init__(self, sigma, lmbda, m, D):
self.sigma = sigma
self.lmbda = lmbda
self.m = m
self.D = D
self.omega, self.u = rff_sample_basis(D, m, sigma)
self._initialise_solution()
def __init__(self, sigma, lmbda, m, D):
self.sigma = sigma
self.lmbda = lmbda
self.m = m
self.D = D
self.omega, self.u = rff_sample_basis(D, m, sigma)
self._initialise_solution()
def test_rff_feature_map_third_order_tensor_theano_execute():
if not theano_available:
raise SkipTest("Theano not available.")
D = 2
x = np.random.randn(D)
m = 10
sigma = 1.
omega, u = rff_sample_basis(D, m, sigma)
for i in range(m):
rff_feature_map_comp_third_order_tensor_theano(x, omega[:, i], u[i])
def test_rff_feature_map_third_order_tensor_theano_execute():
if not theano_available:
raise SkipTest("Theano not available.")
D = 2
x = np.random.randn(D)
m = 10
sigma = 1.
omega, u = rff_sample_basis(D, m, sigma)
for i in range(m):
rff_feature_map_comp_third_order_tensor_theano(x, omega[:, i], u[i])
def test_rff_feature_map_comp_theano_result_equals_manual():
if not theano_available:
raise SkipTest("Theano not available.")
D = 2
x = np.random.randn(D)
m = 10
sigma = 1.
omega, u = rff_sample_basis(D, m, sigma)
phi_manual = rff_feature_map_single(x, omega, u)
for i in range(m):
# phi_manual is a monte carlo average, so have to normalise by np.sqrt(m) here
phi = rff_feature_map_comp_theano(x, omega[:, i], u[i]) / np.sqrt(m)
assert_close(phi, phi_manual[i])
def test_rff_feature_map_comp_theano_result_equals_manual():
if not theano_available:
raise SkipTest("Theano not available.")
D = 2
x = np.random.randn(D)
m = 10
sigma = 1.
omega, u = rff_sample_basis(D, m, sigma)
phi_manual = rff_feature_map_single(x, omega, u)
for i in range(m):
# phi_manual is a monte carlo average, so have to normalise by np.sqrt(m) here
phi = rff_feature_map_comp_theano(x, omega[:, i], u[i]) / np.sqrt(m)
assert_close(phi, phi_manual[i])
def test_rff_feature_map_grad_theano_result_equals_manual():
if not theano_available:
raise SkipTest("Theano not available.")
D = 2
x = np.random.randn(D)
X = x[np.newaxis, :]
m = 10
sigma = 1.
omega, u = rff_sample_basis(D, m, sigma)
grad_manual = rff_feature_map_grad(X, omega, u)[:, 0, :]
for i in range(m):
# phi_manual is a monte carlo average, so have to normalise by np.sqrt(m) here
grad = rff_feature_map_comp_grad_theano(x, omega[:, i], u[i]) / np.sqrt(m)
assert_close(grad, grad_manual[:, i])
def test_rff_feature_map_grad_theano_result_equals_manual():
if not theano_available:
raise SkipTest("Theano not available.")
D = 2
x = np.random.randn(D)
X = x[np.newaxis, :]
m = 10
sigma = 1.
omega, u = rff_sample_basis(D, m, sigma)
grad_manual = rff_feature_map_grad(X, omega, u)[:, 0, :]
for i in range(m):
# phi_manual is a monte carlo average, so have to normalise by np.sqrt(m) here
grad = rff_feature_map_comp_grad_theano(x, omega[:, i],
u[i]) / np.sqrt(m)
assert_close(grad, grad_manual[:, i])
def test_update_b_single_equals_compute_b_when_initialised_correctly():
sigma = 1.
N = 200
D = 2
m = 10
X = np.random.randn(N, D)
# basis
omega, u = rff_sample_basis(D, m, sigma)
# initial fit and update
b_update = np.zeros(m)
n_update = m
for x in X:
b_update = update_b_single(x, b_update, n_update, omega, u)
n_update += 1
# initial fit and batch (average of "fake" b and new observations
b_fake = np.zeros(m)
n_fake = m
b_batch = (b_fake * n_fake + compute_b(X, omega, u) * N) / (n_fake + N)
assert_allclose(b_update, b_batch)
def set_parameters_from_dict(self, param_dict):
EstimatorBase.set_parameters_from_dict(self, param_dict)
# update basis
self.omega, self.u = rff_sample_basis(self.D, self.m, self.sigma)
def set_parameters_from_dict(self, param_dict):
EstimatorBase.set_parameters_from_dict(self, param_dict)
# update basis
self.omega, self.u = rff_sample_basis(self.D, self.m, self.sigma)
