Skip to content
A list of awesome resources on normalizing flows.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
normalizing-flow.svg
readme.md

readme.md

Normalizing Flow

Awesome Normalizing Flows   Awesome

A list of awesome resources for understanding and applying normalizing flows (NF). It's a relatively simple yet powerful new tool in statistics for constructing expressive probability distributions from simple base distribution using smooth bijective transformations (diffeomorphisms).

Publications

  • Dec 5, 2019 - Normalizing Flows for Probabilistic Modeling and Inference by Papamakarios et al. A thorough and very readable review article by some of the guys at DeepMind involved in the development of NF. Highly recommended.
  • May 21, 2015 - Variational Inference with Normalizing Flows by Rezende et al. They show how to go beyond mean field in variational inference by using NF to increase the flexibility of the variational family and make much more complex approximate posteriors possible.
  • Jun 12, 2017 - Multiplicative Normalizing Flows for Variational Bayesian Neural Networks by Louizos et al. With the goal of improving predictive accuracy and uncertainty in Bayesian neural networks, they interpret multiplicative noise in neural network parameters as auxiliary random variables and show how to model these using NF. As in variational inference, the idea is again use NF's power to augment the approximate posterior while maintaining tractability.

Videos

Blog Posts

Code

Open to Suggestions!

Feel free to submit a PR to extend this list.

You can’t perform that action at this time.