Included updated author list (AUTHOR file) and update LICENSE information
Add torch conjugate gradient to dependencies (for forthcoming applications)
Add list of Swyft publications and events to docs
pytorch-lighthing 2.0 compatibility not fully established (pending until 2.0 has feature parity with 1.9)
Add swyft.get_class_probs for extracting classification results from ratio estimators
Add LogRatioEstimator_Gaussian, a Gaussian ratio estimator for arbitrary dimensions
Deprecate LogRatioEstimator_1dim_Gaussian (worked only with 1dim features and 1dim parameters)
Rewritten logratios aggregator in swyft.Module to be more resilient
Add AuxLoss, which just enables to add arbitrary extra losses (e.g. related to regularisation) to the training object
Enable Spectral embedding for parameters in LogRatioEstimator_Ndim for high fidelity posteriors
Add LogRatioEstimator_Autoregressive, an autoregressive neural ratio estimator module
Tutorials completely redone (they are the ones from the Jan 2023 training event)
New documentation theme, and general documentation clean-up
pytorch-lightning 2.0.0 compatibility
Various minor bug fixes and interface improvements.
Release of Swyft with new pytorch-lightning API.
All API components are now in a reasonably stable state, code has been reorganized and docstrings updated. Next steps will include polishing docstrings and generalizing some of the functionality, but should leave the central API components untouched. Swyft has a logo now.
Initial alpha release of Swyft based on pytorch-lightning.