blei-lab/edward

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

4843 stars · 741 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Edward is a Python library for probabilistic modeling, inference, and criticism built on TensorFlow. It supports deep generative models, variational inference, and Monte Carlo methods for research in Bayesian statistics and machine learning.

Use cases

• build bayesian neural networks in tensorflow
• run variational inference on probabilistic models
• fit deep generative models
• do hamiltonian monte carlo sampling
• posterior predictive checks for model criticism
• probabilistic programming for research

When to choose

• you need a flexible testbed for probabilistic modeling research on TensorFlow
• you want variational inference or MCMC for deep probabilistic models

When to avoid

• you need actively maintained tooling - Edward is largely superseded by TensorFlow Probability
• you work outside the TensorFlow 1.x ecosystem

Facets

library · maturity maintenance

machine-learning deep-learning simulation machine-learning deep-learning data-science python cross-platform probabilistic-programming bayesian-inference variational-inference tensorflow monte-carlo generative-models statistics gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="blei-lab/edward")