Skip to main content
Notice removed Draw attention by Durden
Bounty Ended with cinch's answer chosen by Durden
Notice added Draw attention by Durden
Bounty Started worth 50 reputation by Durden
edited title
Link
Nick Cox
  • 59.5k
  • 8
  • 136
  • 212

Why doesn'tdon’t diffusion models suffer posterior collapse?

edited tags
Link
Source Link

Why doesn't diffusion models suffer posterior collapse?

In VAEs, posterior collapse occurs when the approximated posterior $q_\theta(z|x)$ becomes the standard Gaussian prior $p(z)$ after training (Lucas et al. 2019). The forward process of diffusion models transforms the data $x$ into a standard Gaussian at time step $T$, which is similar to approximating the posterior $p(z|x)$ in hierarchical VAEs (see this blog post for more details). Therefore, I am wondering whether diffusion models suffer from the issue of posterior collapse, if that makes sense at all.