zuko
zuko copied to clipboard
probabilists
Normalizing flows in PyTorch
While I was working through the tutorial (which are great!), I took the liberty of refining some wording. I very few mistakes of English language. I also added some bits...
This PR adds changes to the `zuko.flows.mixture.GMM` class, which allow the user to change the type of the covariance matrix used for each of the Gaussian components of the mixture....
### Description Currently, the `zuko.flows.mixture.GMM` class only supports full covariance matrices. However, there are a number of use cases (especially high-dimensional) where a full covariance matrix is either not needed...
I've found the Zuko library to be extremely beneficial for my work. I sincerely appreciate the effort that has gone into its development. In the Masked Autoregressive Flow paper (NeurIPS,...
### Description Hello @francois-rozet, This should take up our discussion on the usage of star imports in #38: Using star imports in Python is very convenient and saves you from...
## Description This issue tracks the flow/transformation architectures that are requested and/or implemented. You are welcome to request new architectures. If you wish to contribute to Zuko, this list is...
### Description Glow is multi-scale normalizing flow based on affine coupling transforms introduced in [Glow: Generative Flow with Invertible 1x1 Convolutions](https://arxiv.org/abs/1807.03039) (Kingma et al., 2018). ### Implementation Due to its...
This is an implementation of #53, in which I add support to provide an adjacency matrix to the autoregressive models, instead of using the ordering between variables. I have added...
### Description I would like to enable support for autoregressive models (that is, MAF, NSF, and NAF) to use a specific adjacency matrix (rather than an ordering), which could be...