tf.contrib.distributions.Mixture.entropy_lower_bound(name='entropy_lower_bound')
A lower bound on the entropy of this mixture model.
The bound below is not always very tight, and its usefulness depends on the mixture probabilities and the components in use.
A lower bound is useful for ELBO when the Mixture
is the variational distribution:
logp(x)>=ELBO=∫q(z)logp(x,z)dz+H[q]
where p is the prior disribution, q is the variational, and H[q] is the entropy of q. If there is a lower bound G[q] such that H[q]≥G[q] then it can be used in place of H[q].
For a mixture of distributions q(Z)=∑iciqi(Z) with ∑ici=1, by the concavity of f(x)=−xlogx, a simple lower bound is:
H[q]=−∫q(z)logq(z)dz =−∫(∑iciqi(z))log(∑iciqi(z))dz ≥−∑ici∫qi(z)logqi(z)dz =∑iciH[qi]
This is the term we calculate below for G[q].
Args:
-
name
: A name for this operation (optional).
Returns:
A lower bound on the Mixture's entropy.
Please login to continue.