Merge pull request #2223 from pymc-devs/bump_v3.1rc4

Bump version to 3.1rc4

Author: twiecki

CHANGELOG.md

@@ -1,13 +1,29 @@
 # Release Notes
 
-## PyMC3 3.1 (TBA)
+## PyMC3 3.1 (June 23, 2017)
 
 ### New features
 
-* [Add Gaussian Process submodule](http://pymc-devs.github.io/pymc3/notebooks/GP-introduction.html)
+* New user forum at http://discourse.pymc.io
+
+* [Gaussian Process submodule](http://pymc-devs.github.io/pymc3/notebooks/GP-introduction.html)
+
+* Much improved variational inference support:
+
+  - [Add Operator Variational Inference (experimental).](http://pymc-devs.github.io/pymc3/notebooks/bayesian_neural_network_opvi-advi.html)
+
+  - [Add Stein-Variational Gradient Descent as well as Amortized SVGD (experimental).](https://github.com/pymc-devs/pymc3/pull/2183)
+
+  - [Add pm.Minibatch() to easily specify mini-batches.](http://pymc-devs.github.io/pymc3/notebooks/bayesian_neural_network_opvi-advi.html#Minibatch-ADVI)
+
+  - Added various optimizers including ADAM.
+  
+  - Stopping criterion implemented via callbacks.
 
 * sample() defaults changed: tuning is enabled for the first 500 samples which are then discarded from the trace as burn-in.
 
+* MvNormal supports Cholesky Decomposition now for increased speed and numerical stability.
+
 * Many optimizations and speed-ups.
 
 * NUTS implementation now matches current Stan implementation.
@@ -28,24 +44,32 @@
 
 * Much improved variational inference support:
 
-  - [Add Operator Variational Inference (experimental).](http://pymc-devs.github.io/pymc3/notebooks/bayesian_neural_network_opvi-advi.html)
+  - [Added Operator Variational Inference (experimental).](http://pymc-devs.github.io/pymc3/notebooks/variational_api_quickstart.html)
 
-  - [Add Stein-Variational Gradient Descent as well as Amortized SVGD (experimental).](https://github.com/pymc-devs/pymc3/pull/2183)
+  - [Added Stein-Variational Gradient Descent as well as Amortized SVGD (experimental).](https://github.com/pymc-devs/pymc3/pull/2183)
 
-  - [Add pm.generator() to easily specify mini-batches.](http://pymc-devs.github.io/pymc3/notebooks/bayesian_neural_network_opvi-advi.html#Minibatch-ADVI)
+  - [Added `Minibatch` to easily specify mini-batches.](http://pymc-devs.github.io/pymc3/notebooks/bayesian_neural_network_opvi-advi.html#Minibatch-ADVI)
+  
+  - Added full-rank ADVI
 
   - Added various optimizers including ADAM.
+  
+  - Deprecated old ADVI interface
+  
+  - implemented `fit` function as the primary interface to approximation algorithms
+
+* Added support for multidimensional minibatches
 
 * [Sampled posteriors can now be turned into priors for Bayesian updating with a new interpolated distribution.](https://github.com/pymc-devs/pymc3/pull/2163)
 
+* Added `Approximation` class and the ability to convert a sampled trace into an approximation via its `Empirical` subclass.
+
 * `Model` can now be inherited from and act as a base class for user specified models (see pymc3.models.linear).
 
 * Add MvGaussianRandomWalk and MvStudentTRandomWalk distributions.
 
 * GLM models do not need a left-hand variable anymore.
 
-* Add support for cholesky parametrizations for cov/corr matrices.
-
 * Refactored HMC and NUTS for better readability.
 
 * Add support for Python 3.6.

RELEASE-NOTES.md

@@ -78,7 +78,7 @@
 # The short X.Y version.
 version = '3.1'
 # The full version, including alpha/beta/rc tags.
-release = '3.1rc3'
+release = '3.1rc4'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/source/conf.py

@@ -1,5 +1,5 @@
 # pylint: disable=wildcard-import
-__version__ = "3.1rc3"
+__version__ = "3.1rc4"
 
 from .blocking import *
 from .distributions import *

docs/source/notebooks/Diagnosing_biased_Inference_with_Divergences.ipynb

@@ -125,7 +125,7 @@ def random_choice(*args, **kwargs):
             else:
                 return np.random.choice(k, p=w, *args, **kwargs)
 
-        w = draw_values([self.w], point=point)
+        w = draw_values([self.w], point=point)[0]
 
         w_samples = generate_samples(random_choice,
                                      w=w,

docs/source/notebooks/GLM-hierarchical-advi-minibatch.ipynb

@@ -13,7 +13,7 @@
 AUTHOR_EMAIL = '[email protected]'
 URL = "http://github.com/pymc-devs/pymc3"
 LICENSE = "Apache License, Version 2.0"
-VERSION = "3.1rc3"
+VERSION = "3.1rc4"
 
 classifiers = ['Development Status :: 5 - Production/Stable',
                'Programming Language :: Python',