Papers › Discouraging posterior collapse in hierarchical Variational Autoencoders using context

Discouraging posterior collapse in hierarchical Variational Autoencoders using context

20 Feb 2023arXiv:2302.09976archive 2025-07-28

Anna Kuzina, Jakub M. Tomczak

Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models. There is a consensus that the top-down hierarchical VAEs allow effective learning of deep latent structures and avoid problems like posterior collapse. Here, we show that this is not necessarily the case, and the problem of collapsing posteriors remains. To discourage this issue, we propose a deep hierarchical VAE with a context on top. Specifically, we use a Discrete Cosine Transform to obtain the last latent variable. In a series of experiments, we observe that the proposed modification allows us to achieve better utilization of the latent space and does not harm the model's generative abilities.

PaperPDFCode

Code

akuzina/dvp_vae officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Discrete Cosine TransformHierarchical VAE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections