Releases: secondmind-labs/trieste
Release 4.5.1
Fixes
Fix one hot encoder to use input dtype and not space dtype when encoding (not normally an issue, but less fragile) (#913)
Full Changelog: v4.5.0...v4.5.1
Release 4.5.0
Improvements
GPflow model wrappers can be initialised with a pre-generated posterior cache (#911)
FrozenOptimizer can be used when required for models that are frozen and no longer support optimization (#911)
Full Changelog: v4.4.0...v4.5.0
Release v4.4.0
Improvements/fixes
TF datasets are now passed to DeepEnsemble.model.fit. This change enables support for training over a specified number of steps (rather than a set number of epochs) for small datasets, which may require data repetition to achieve the desired step count. #907
An optional predict_fn parameter has been added to IndependentReparametrizationSampler.init. This parameter allows generating samples where the mean and variance come from sources other than model.predict. This feature is particularly useful for drawing samples from models that separate epistemic and aleatoric uncertainty, providing greater flexibility in controlling the sources of uncertainty in the generated samples. #903
Release v4.3.0
Improvements/fixes
implement predict_y and predict_noise for Deep Ensemble models, and update predict to more appropriately return the epistemic uncertainty #894
fix jitter bug in Deep Ensemble trajectory sampler #900
Full Changelog: v4.2.4...v4.3.0
Release v4.2.4
Fixes
Remove default independent reparametrization sampler jitter (but ensure positive variance) (#888)
Test against TF 2.14 (#895)
Full Changelog: v4.2.3...v4.2.4
Release 4.2.3
Fixes
Fix DeepEnsemble model serialization for some versions of tensorflow (#892)
Full Changelog: v4.2.2...v4.2.3
Release 4.2.2
Fixes
- Don't use the same seed when sampling from the subspaces of a product space [#885]
- Fix failing ray tutorial [#856]
Full Changelog: v4.2.1...v4.2.2
Release 4.2.1
Fixes
Make one hot encoder compilable (#880)
Improve dataset_len error message (#879)
Full Changelog: v4.2.0...v4.2.1
Release 4.2.0
Improvements/fixes
Avoid duplicating initial points when using vectorization (#875)
Full Changelog: v4.1.0...v4.2.0
Release 4.1.0
Improvements/fixes
Query point encoders for Deep GP models (#873)
Full Changelog: v4.0.1...v4.1.0