tf.contrib.bayesflow.entropy.entropy_shannon(p, z=None, n=None, seed=None, form=None, name='entropy_shannon') Monte Carlo or deterministic
tf.contrib.bayesflow.entropy.elbo_ratio(log_p, q, z=None, n=None, seed=None, form=None, name='elbo_ratio') Estimate of the ratio
KL[q || p] If log_p(z) = Log[p(z)] for distribution p, this Op approximates the negative
tf.contrib.bayesflow.entropy.renyi_ratio(log_p, q, alpha, z=None, n=None, seed=None, name='renyi_ratio') Monte Carlo estimate
tf.contrib.bayesflow.entropy.renyi_alpha(step, decay_time, alpha_min, alpha_max=0.99999, name='renyi_alpha') Exponentially decaying