# Edward: A library for probabilistic modeling, inference, and criticism

arXiv: https://arxiv.org/abs/1610.09787 · HTML: https://mlsanity.com/paper/1610.09787/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2016.

## Built on by (most cited first, 28 of 28)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [NeuralUQ: A comprehensive library for uncertainty quantification in neural differential equations and operators](https://mlsanity.com/paper/2208.11866/) (2022)
- [Local convexity of the TAP free energy and AMP convergence for Z2-synchronization](https://mlsanity.com/paper/2106.11428/) (2021)
- [Causal Mediation Analysis with Hidden Confounders](https://mlsanity.com/paper/2102.11724/) (2021)
- [Empirical Evaluation of Biased Methods for Alpha Divergence Minimization](https://mlsanity.com/paper/2105.06587/) (2021)
- [Automatic variational inference with cascading flows](https://mlsanity.com/paper/2102.04801/) (2021)
- [Breiman's two cultures: You don't have to choose sides](https://mlsanity.com/paper/2104.12219/) (2021)
- [Learning Proposals for Probabilistic Programs with Inference Combinators](https://mlsanity.com/paper/2103.00668/) (2021)
- [Foundation Posteriors for Approximate Probabilistic Inference](https://mlsanity.com/paper/2205.09735/) (2022)
- [Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference](https://mlsanity.com/paper/2208.10530/) (2022)
- [Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling](https://mlsanity.com/paper/2110.06021/) (2021)
- [BayesPerf: Minimizing Performance Monitoring Errors Using Bayesian Statistics](https://mlsanity.com/paper/2102.10837/) (2021)
- [Meta-Learning an Inference Algorithm for Probabilistic Programs](https://mlsanity.com/paper/2103.00737/) (2021)
- [MINIMALIST: Mutual INformatIon Maximization for Amortized Likelihood Inference from Sampled Trajectories](https://mlsanity.com/paper/2106.01808/) (2021)
- [Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility](https://mlsanity.com/paper/2109.04561/) (2021)
- [Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge](https://mlsanity.com/paper/2202.09248/) (2022)
- [Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation](https://mlsanity.com/paper/2509.01330/) (2025)
- [Variational Inference for Category Recommendation in E-Commerce platforms](https://mlsanity.com/paper/2104.07748/) (2021)
- [Boosting Variational Inference With Locally Adaptive Step-Sizes](https://mlsanity.com/paper/2105.09240/) (2021)
- [Expectation Programming: Adapting Probabilistic Programming Systems to Estimate Expectations Efficiently](https://mlsanity.com/paper/2106.04953/) (2021)
- [Pixyz: a Python library for developing deep generative models](https://mlsanity.com/paper/2107.13109/) (2021)
- [Unifying AI Algorithms with Probabilistic Programming using Implicitly Defined Representations](https://mlsanity.com/paper/2110.02325/) (2021)
- [On Reinforcement Learning, Effect Handlers, and the State Monad](https://mlsanity.com/paper/2203.15426/) (2022)
- [Borch: A Deep Universal Probabilistic Programming Language](https://mlsanity.com/paper/2209.06168/) (2022)
- [Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks](https://mlsanity.com/paper/2308.00231/) (2023)
- [Probabilistic Answer Set Programming with Discrete and Continuous Random Variables](https://mlsanity.com/paper/2409.20274/) (2024)
- [Identifying latent disease factors differently expressed in patient subgroups using group factor analysis](https://mlsanity.com/paper/2410.07890/) (2024)

## Abstract (arXiv)

Probabilistic modeling is a powerful approach for analyzing empirical information. We describe Edward, a library for probabilistic modeling. Edward's design reflects an iterative process pioneered by George Box: build a model of a phenomenon, make inferences about the model given data, and criticize the model's fit to the data. Edward supports a broad class of probabilistic models, efficient algorithms for inference, and many techniques for model criticism. The library builds on top of TensorFlow to support distributed training and hardware such as GPUs. Edward enables the development of complex probabilistic models and their algorithms at a massive scale.