Groups
Variational Inference (VI) turns Bayesian inference into an optimization problem by choosing a simple family q(z) to approximate an intractable posterior p(z|x).
The reparameterization trick rewrites a random variable as a deterministic function of noise that does not depend on the parameters, such as z = ฮผ + ฯ ยท ฮต with ฮต ~ N(0, 1).