BayesFlow Versions Save

What's Changed

• Hotfix pip installation error with Apple Silicon by @marvinschmitt in https://github.com/stefanradev93/BayesFlow/pull/155

Full Changelog: https://github.com/stefanradev93/BayesFlow/compare/v1.1.5...v1.1.6

What's Changed

• set label names in plot_recovery() by @levolz in https://github.com/stefanradev93/BayesFlow/pull/102
• Development by @stefanradev93 in https://github.com/stefanradev93/BayesFlow/pull/103
• add label_fontsize and value_fontsize by @LuSchumacher in https://github.com/stefanradev93/BayesFlow/pull/106
• Optimization: add setting for tqdm mininterval by @vpratz in https://github.com/stefanradev93/BayesFlow/pull/108
• add n_row and n_col argument where applicable by @LuSchumacher in https://github.com/stefanradev93/BayesFlow/pull/109
• fix some typos and out-of-sync docstrings by @daniel-habermann in https://github.com/stefanradev93/BayesFlow/pull/111
• add **kwargs to diagnostics.plot_recovery by @marvinschmitt in https://github.com/stefanradev93/BayesFlow/pull/112
• Merge with dev by @stefanradev93 in https://github.com/stefanradev93/BayesFlow/pull/115
• Minor improvements by @elseml in https://github.com/stefanradev93/BayesFlow/pull/117
• Update README.md with forum by @elseml in https://github.com/stefanradev93/BayesFlow/pull/116
• update tutorial notebook 1 by @rusty-electron in https://github.com/stefanradev93/BayesFlow/pull/120
• Minimal Fix for Broken Tests by @LarsKue in https://github.com/stefanradev93/BayesFlow/pull/130
• Drop Support for Python 3.9, Add Support for Python 3.11 by @LarsKue in https://github.com/stefanradev93/BayesFlow/pull/132
• fix tutorial notebook 1 toc links and update some text by @rusty-electron in https://github.com/stefanradev93/BayesFlow/pull/136
• Make diagnostic plots work with one-parameter models by @Kucharssim in https://github.com/stefanradev93/BayesFlow/pull/137
• Fix offline training for model comparison ignoring shared context by @elseml in https://github.com/stefanradev93/BayesFlow/pull/139
• README - update minimal example by @vpratz in https://github.com/stefanradev93/BayesFlow/pull/141
• update TOCs of example notebooks by @rusty-electron in https://github.com/stefanradev93/BayesFlow/pull/142
• Bump up to Series 1.1.5 update by @stefanradev93 in https://github.com/stefanradev93/BayesFlow/pull/143
• add notebook: amortized point estimation by @vpratz in https://github.com/stefanradev93/BayesFlow/pull/145
• Bayes Estimators: Loss functions with flexible signature by @han-ol in https://github.com/stefanradev93/BayesFlow/pull/147
• Development by @stefanradev93 in https://github.com/stefanradev93/BayesFlow/pull/150

New Contributors

• @daniel-habermann made their first contribution in https://github.com/stefanradev93/BayesFlow/pull/111
• @rusty-electron made their first contribution in https://github.com/stefanradev93/BayesFlow/pull/120
• @LarsKue made their first contribution in https://github.com/stefanradev93/BayesFlow/pull/130
• @Kucharssim made their first contribution in https://github.com/stefanradev93/BayesFlow/pull/137
• @han-ol made their first contribution in https://github.com/stefanradev93/BayesFlow/pull/147

Full Changelog: https://github.com/stefanradev93/BayesFlow/compare/v1.1.4...v1.1.5

State of software at JOSS publication.

1. Bugfix in SimulationMemory affecting the use of empty folders for initializing a Trainer;
2. Bugfix in Trainer.train_from_presimulation() for model comparison tasks;
3. Added a classifier two-sample test (C2ST) function c2st in computational_utilities.

1. Bugfix related to training SetTransformer with induced points
2. Bugfix for offline training of transformers with variable sizes
3. Complete revamp of documentation, README, and tutorials

Enable PyPI integration through GitHub workflows.

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. :)

Welcome to the Future!