Skip to content

Beyond Beta!
Compare
Choose a tag to compare
@stefanradev93 stefanradev93 released this 22 Jun 13:54
· 192 commits to master since this release
v1.1
29f0b95
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

Following multiple improvements and being actively used in multiple projects, the BayesFlow library is ready to move beyond the beta phase!

Features:

  1. Added option for permutation='learnable' when creating an InvertibleNetwork
  2. Added option for coupling_design in ["affine", "spline", "interleaved"] when creating an InvertibleNetwork
  3. Simplified passing additional settings to the internal networks. For instance, you
    can now simply do
    inference_network = InvertibleNetwork(num_params=20, coupling_net_settings={'mc_dropout': True})
    to get a Bayesian neural network.
  4. PMPNetwork has been added for model comparison according to findings in https://arxiv.org/abs/2301.11873
  5. Publication-ready calibration diagnostic for expected calibration error (ECE) in a model comparison setting has been
    added to diagnostics.py and is accessible as plot_calibration_curves()
  6. A new module experimental has been added currently containing rectifiers.py.
  7. Default settings for transformer-based architectures.
  8. Numerical calibration error using posterior_calibration_error()

General Improvements:

  1. Improved docstrings and consistent use of keyword arguments vs. configuration dictionaries
  2. Increased focus on transformer-based architectures as summary networks
  3. Figures resulting diagnostics.py have been improved and prettified
  4. Added a module sensitivity.py for testing the sensitivity of neural approximators to model misspecification
  5. Multiple bugfixes, including a major bug affecting the saving and loading of learnable permutations

The project now also features automatic PyPI publishing. :)

Assets 2
Loading