blei-lab/edward


A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

http://edwardlib.org

License: Other

Language: Jupyter Notebook

Keywords: bayesian-methods, data-science, deep-learning, machine-learning, neural-networks, probabilistic-programming, statistics, tensorflow


edward

Build Status Coverage Status Join the chat at https://gitter.im/blei-lab/edward

Edward is a Python library for probabilistic modeling, inference, and criticism. It is a testbed for fast experimentation and research with probabilistic models, ranging from classical hierarchical models on small data sets to complex deep probabilistic models on large data sets. Edward fuses three fields: Bayesian statistics and machine learning, deep learning, and probabilistic programming.

It supports modeling with

  • Directed graphical models
  • Neural networks (via libraries such as Keras and TensorFlow Slim)
  • Implicit generative models
  • Bayesian nonparametrics and probabilistic programs

It supports inference with

  • Variational inference
    • Black box variational inference
    • Stochastic variational inference
    • Generative adversarial networks
    • Maximum a posteriori estimation
  • Monte Carlo
    • Gibbs sampling
    • Hamiltonian Monte Carlo
    • Stochastic gradient Langevin dynamics
  • Compositions of inference
    • Expectation-Maximization
    • Pseudo-marginal and ABC methods
    • Message passing algorithms

It supports criticism of the model and inference with

  • Point-based evaluations
  • Posterior predictive checks

Edward is built on top of TensorFlow. It enables features such as computational graphs, distributed training, CPU/GPU integration, automatic differentiation, and visualization with TensorBoard.

Resources

See Getting Started for how to install Edward.

Project Statistics

Sourcerank 11
Repository Size 28.5 MB
Stars 3,991
Forks 710
Watchers 296
Open issues 199
Dependencies 2
Contributors 72
Tags 28
Created
Last updated
Last pushed

Top Contributors See all

Dustin Tran Alp Kucukelbir Maja Rudolph Adji Bousso Dieng Dawen Liang Siddharth Agrawal Matt Hoffman Lyndon Ollar cbonnett Nick Foti KonstantinLukaschenko Christopher Prohm John Pearson Bhargav Srinivasa Desikan Dr. Kashif Rasul James Webber Jeremy Kerfs Robert William Wolf Thomas Wiecki

Packages Referencing this Repo

Edward
A library for probabilistic modeling, inference, and criticism
Latest release 1.3.5 - Updated - 3.99K stars

Recent Tags See all

1.3.5 January 22, 2018
1.3.4 September 28, 2017
1.3.3 June 16, 2017
1.3.2 May 30, 2017
1.3.1 April 27, 2017
1.3.0 April 27, 2017
1.2.4 March 20, 2017
1.2.3 March 08, 2017
1.2.2 February 28, 2017
1.2.1 January 30, 2017
1.2.0 January 16, 2017
1.1.6 December 13, 2016
1.1.5 November 16, 2016
1.1.4 November 02, 2016
1.1.3 October 03, 2016

Interesting Forks See all

twiecki/edward
A library for probabilistic modeling, inference, and criticism. Deep generative models, variation...
Python - Last pushed - 2 stars
dataoverflow/edward
A library for probabilistic modeling, inference, and criticism. Deep generative models, variation...
Python - Other - Last pushed - 1 stars
matthewdhoffman/edward
A library for probabilistic modeling, inference, and criticism. Deep generative models, variation...
Python - Updated - 1 stars
carryAiYu/edward
A library for probabilistic modeling, inference, and criticism. Deep generative models, variation...
Jupyter Notebook - Updated - 1 stars
chrinide/edward
A library for probabilistic modeling, inference, and criticism. Deep generative models, variation...
Jupyter Notebook - Updated - 1 stars

Something wrong with this page? Make a suggestion

Last synced: 2018-01-22 06:42:24 UTC

Login to resync this repository