Undirected Graphical Models as Approximate Posteriors

By Arash Vahdat, Evgeny Andriyash, William G. Macready. 2019

15 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

1. Josh Tenenbaum
2. Arash Vahdat
3. Shuang Li
4. Yilun Du
5. Jan Kautz
6. Karsten Kreis
7. Igor Mordatch
8. Yang Song

Citations in the corpus

• Score-based Generative Modeling in Latent Space (2021, background): “For example, Normalizing flows and hierarchical distributions [23, 24, 47, 48, 20, 21], as well as energy-based models [49, 50, 51, 52, 53] have been proposed as VAE priors.”
• Improved Contrastive Divergence Training of Energy Based Models (2020, methodology): “To reduce the memory overhead of this differentiation procedure, we only differentiate through the last step of Langevin sampling as also done in (Vahdat et al., 2020).”