Release Notes

This is the 0.5.0 release of TensorFlow Probability. It's tested and stable against TensorFlow 1.12.

Packaging Change

As of this release, we no longer package a separate GPU-specific build. Users can select the version of TensorFlow they wish to use (CPU or GPU), and TensorFlow Probability will work with both.

As a result, we no longer explicitly list a TensorFlow dependency in our package requirements (since we can't know which version the user will want). If TFP is installed with no TensorFlow package present, or with an unsupported TensorFlow version, we will issue an ImportError at time of import.

Distributions & Bijectors

• All Distributions have been relocated from tf.distributions to tfp.distributions (the ones in TF are deprecated and will be deleted in TF 2.0).
• Add Triangular distribution.
• Add Zipf distribution.
• Add NormalCDF Bijector.
• Add Multivariate Student's t-distribution.
• Add RationalQuadratic kernel.

Documentation & Examples

• Add example showing how to fit GLMM using Variational Inference.
• Introduce Gaussian process latent variable model colab.
• Introduce Gaussian process regression example colab
• Add notebook showcasing GLM algorithms and deriving some results about GLMs that those algorithms leverage.

Huge thanks to all the contributors to this release!

• Akshay Modi
• Alexey Radul
• Anudhyan Boral
• Ashish Saxena
• Ben Zinberg
• Billy Lamberta
• Brian Patton
• Christopher Suter
• Dave Moore
• Ian Langmore
• Joshua V. Dillon
• Kristian Hartikainen
• Malcolm Reynolds
• Pavel Sountsov
• Srinivas Vasudevan
• Xiaojing Wang
• Yifei Feng