def test_gaussian_GFE_derivatives_self_consistent():
num_units = 5
layer_1 = layers.GaussianLayer(num_units)
layer_2 = layers.BernoulliLayer(num_units)
rbm = BoltzmannMachine([layer_1, layer_2])
for i in range(len(rbm.connections)):
rbm.connections[i].weights.params.matrix[:] = \
0.01 * be.randn(rbm.connections[i].shape)
for lay in rbm.layers:
lay.params.loc[:] = be.rand_like(lay.params.loc)
state, cop1_GFE = rbm._compute_StateTAP_self_consistent()
grad = rbm._grad_gibbs_free_energy(state)
gu.grad_normalize_(grad)
for i in range(100):
lr = 0.1
gogogo = True
random_grad = gu.random_grad(rbm)
gu.grad_normalize_(random_grad)
while gogogo:
cop1 = deepcopy(rbm)
lr_mul = partial(be.tmul, lr)
cop1.parameter_update(gu.grad_apply(lr_mul, grad))
cop1_state, cop1_GFE = cop1._compute_StateTAP_self_consistent()
cop2 = deepcopy(rbm)
cop2.parameter_update(gu.grad_apply(lr_mul, random_grad))
cop2_state, cop2_GFE = cop2._compute_StateTAP_self_consistent()
regress = cop2_GFE - cop1_GFE < 0.0
if regress:
if lr < 1e-6:
assert False, \
"TAP FE gradient is not working properly for Gaussian models"
break
else:
lr *= 0.5
else:
break
def test_gaussian_Compute_StateTAP_self_consistent():
num_units = 10
layer_1 = layers.GaussianLayer(num_units)
layer_2 = layers.BernoulliLayer(num_units)
rbm = BoltzmannMachine([layer_1, layer_2])
for i in range(len(rbm.connections)):
rbm.connections[i].weights.params.matrix[:] = \
0.01 * be.randn(rbm.connections[i].shape)
for lay in rbm.layers:
lay.params.loc[:] = be.rand_like(lay.params.loc)
for i in range(100):
random_state = StateTAP.from_model_rand(rbm)
GFE = rbm.gibbs_free_energy(random_state.cumulants)
_,min_GFE = rbm._compute_StateTAP_self_consistent(seed=random_state)
if GFE - min_GFE < 0.0:
assert False, \
"compute_StateTAP_self_consistent is not reducing the GFE"
