VincentStimper Normalizing Flows Versions Save

• CoupledRationalQuadraticSpline flow can now be used with conditioning
• Neural spline flow can be used with automatic mixed precision
• Updated Used by list

• Added ConditionalNormalizingFlow addressing the issues #9 and #41
• Removed lambda functions used in neural spline flow to allow flow models to be pickled, see issue #43

• Added reference to paper published in JOSS
• Added CITATION.cff file

• Added examples, including multiscale architecture and change of base distribution
• Added examples to the documentation
• Forward and inverse with log det method to multiscale architecture
• Target distribution for augmented normalizing flow

• Removed debugging print statement
• Fixed bug in forward_and_log_det method, that has recently been introduced

• Paper about the package published on arXiv
• Citation note added

• Added forward and inverse method to flow module
• Added more tests and fix bugs, e.g. relating variational autoencoder
• Added automatic tests and coverage analysis on GitHub

A rendered documentation is added to the repository, which is available on https://vincentstimper.github.io/normalizing-flows/.

Test were added for several flow modules, which can be run via pytest. With these new tests, several bugs were detected and fixed. The current coverage is about 61%. More tests will be added in the future as well as automated testing and coverage analysis on GitHub.

Moreover, the code is adapted to the syntax of newer PyTorch Versions.

The package is now available on PyPI, which means that it can just be installed with

pip install normflows

from now on. The code was reformatted to conform to the black coding style.

Moreover, the following fixes and additions are included:

• The computation of the alpha-divergence objective was corrected.
• A bug regarding sampling from the mixture of Gaussian base distribution was fixed.
• A flow layer to warp periodic variables was added.
• The dependency from the Residual Flow repository was removed.

The code was reorganized to be more hierarchical and readable. Also all required functionality for Neural Spline Flows were added to the repository to remove the dependency on the original Neural Spline Flow repository.

Furthermore, the following features were introduced:

• Class to reverse a flow layer
• Class to build a chain of flow layers
• Affine Masked Autoregressive Flows (MAF)
• Circular Neural Spline Flows
• Neural Spline Flows with circular and non-circular coordinates