Iterative Refinement of the Approximate Posterior for Directed Belief Networks
NIPS, pp. 4691-4699, 2016.
Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods. Recent advances that exploit the capacity and flexibility in this approach have expanded what kinds of models can be trained. However, as a proposal for the posterior, ...More
Full Text (Upload PDF)
PPT (Upload PPT)