def test_vectorized_SGLD(self):
np.random.seed(0)
X = np.arange(5)-2.0
b=2.31
a = 0.01584
epsilons = a*(b+np.arange(5))**(-0.55)
r1 = evSGLD(manual_grad,grad_log_prior,X,n=1,epsilons=epsilons,theta=np.array([1.,1.3]))
np.random.seed(0)
r2 = SGLD(manual_grad,grad_log_prior,X,n=1,chain_size=5,theta=np.array([1.,1.3]))
assert_almost_equal(r1,r2)
def test_vectorized_SGLD(self):
np.random.seed(0)
X = np.arange(5) - 2.0
b = 2.31
a = 0.01584
epsilons = a * (b + np.arange(5))**(-0.55)
r1 = evSGLD(manual_grad,
grad_log_prior,
X,
n=1,
epsilons=epsilons,
theta=np.array([1., 1.3]))
np.random.seed(0)
r2 = SGLD(manual_grad,
grad_log_prior,
X,
n=1,
chain_size=5,
theta=np.array([1., 1.3]))
assert_almost_equal(r1, r2)
SAMPLE_SIZE
from sgld_test.likelihoods import gen_X, log_probability
import numpy as np
np.random.seed(SEED)
X = gen_X(SAMPLE_SIZE)
def vectorized_log_density(theta):
return log_probability(theta,X)
t1 = time()
sample = []
no_chains = NUMBER_OF_TESTS * NO_OF_SAMPELS_IN_TEST
for i in range(no_chains):
if i % (100) == 0:
print(float(i)*100.0/no_chains)
print(time()-t1)
sample.append(evSGLD(manual_grad, grad_log_prior, X, n=1, chain_size=SGLD_CHAIN_SIZE,theta = np.random.randn(2) ) )
sample = np.array(sample)
np.save('samples.npy',sample)
import numpy as np
np.random.seed(SEED)
X = gen_X(SAMPLE_SIZE)
def vectorized_log_density(theta):
return log_probability(theta, X)
t1 = time()
sample = []
no_chains = NUMBER_OF_TESTS * NO_OF_SAMPELS_IN_TEST
for i in range(no_chains):
if i % (100) == 0:
print(float(i) * 100.0 / no_chains)
print(time() - t1)
sample.append(
evSGLD(manual_grad,
grad_log_prior,
X,
n=1,
chain_size=SGLD_CHAIN_SIZE,
theta=np.random.randn(2)))
sample = np.array(sample)
np.save('samples.npy', sample)
