def log_prior(self, leaf_values):
return T.mean(
log_normal(leaf_values,
T.zeros_like(leaf_values, dtype='float32'),
T.ones_like(leaf_values, dtype='float32'),
self.embedding_size,
dim=2))
def log_likelihood(self, states, costs):
mean = self.evaluate(states)
stdev = T.ones_like(mean) * self.stdev
return stats.GaussianScaleDiag([
stdev, mean
]).log_likelihood(costs)
def _sample(self, num_samples):
a = self.get_parameters('natural')[Stats.X]
d = self.shape()[-1]
gumbel_noise = Gumbel(T.zeros_like(a), T.ones_like(a)).sample(num_samples)
return T.one_hot(T.argmax(a[None] + gumbel_noise, -1), d)