Metadata-Version: 2.0
Name: varibayes
Version: 0.0.1
Summary: A toolbox for performing variational Bayesian inference
Home-page: https://github.com/colinclement/varibayes
Author: Colin Clement
Author-email: colin.clement@gmail.com
License: MIT License
Keywords: variational bayes inference
Platform: any
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Science/Research
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Scientific/Engineering :: Mathematics
Requires-Dist: numpy (>=1.10.4)

Variational Bayesian Inference Toolbox

--------------------------------------


This module is inspired by the paper 'Black Box Variational Inference'
by Rajesh Ranganath et al. It attempts to make nearly trivial the task
of fitting a variational distribution to a user-specified log-likelihood
function without derivatives. Currently it only uses a
mean field variational distribution, but the main class 
VariationalInferenceMF is flexible enough for simple subclassing in the
future. This module also contains a number of implementations of
stochastic gradient descent algorithms to be used for optimization.


