This python library is an extension of pytorch🔥 for transforming ordinary neural networks into Bayesian. Why? Check out our post for motivation and approaches in this topic. You will find here foundamental ideas and practical considerations about Bayesian inference.
Our docs pages, blog and more are available on Github Pages.
See examples/ for basic building of Bayesian nets and their training.
Make sure you have poetry installed and run the following in the project's root
poetry install
To run tests with coverage
poetry run pytest --cov=src tests/
- Ilgam Latypov
- Alexander Terentyev
- Kirill Semkin
- Nikita Mashalov
Here are the works upon which this library is built
-
Graves, A. (2011). Practical Variational Inference for Neural Networks. In Advances in Neural Information Processing Systems. Curran Associates, Inc.
-
Christos Louizos, Karen Ullrich, & Max Welling. (2017). Bayesian Compression for Deep Learning.
-
Hippolyt Ritter, Aleksandar Botev, & David Barber (2018). A Scalable Laplace Approximation for Neural Networks. In International Conference on Learning Representations.
-
Yingzhen Li, & Richard E. Turner. (2016). Renyi Divergence Variational Inference.