Groups
Category
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).
Variational Inference (VI) replaces an intractable posterior with a simpler distribution and optimizes it by minimizing KL divergence, which is equivalent to maximizing the ELBO.