no code implementations • 23 Apr 2022 • Jacobie Mouton, Steve Kroon
Subsequent work has explored incorporating more complex distributions and dependency structures: including normalizing flows in the encoder network allows latent variables to entangle non-linearly, creating a richer class of distributions for the approximate posterior, and stacking layers of latent variables allows more complex priors to be specified for the generative model.
no code implementations • 23 Apr 2022 • Jacobie Mouton, Steve Kroon
Furthermore, our model provides performance competitive with other graphical flows for both density estimation and inference tasks.