Semi-Implicit Variational Inference
ICML, 2018.
EI
Abstract:
Semi-implicit variational inference (SIVI) is introduced to expand the commonly used analytic variational distribution family, by mixing the variational parameter with a flexible distribution. This mixing distribution can assume any density function, explicit or not, as long as independent random samples can be generated via reparameter...More
Code:
Data:
Tags
Comments