Variational Inference

1 · Dane Andrew Williamson · May 5, 2022, midnight
What is Variational Inference? Variational Inference is a technique used in Bayesian Statistics to approximate $p ( z \mid x)$ the conditional density of an unknown variable, z given an observed variable, x through optimization. To find this approximate density: select a family of densities, $\mathscr{D}$ over the latent variables. Each member of the family q(z) $\in \mathscr{D}$ is a candidate approximation to the true density. The optimization problem is then to find the member of this family ...