# Deep Probabilistic Programming

arXiv: https://arxiv.org/abs/1701.03757 · HTML: https://mlsanity.com/paper/1701.03757/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2017.

## Built on by (most cited first, 24 of 24)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Neural Probabilistic Logic Programming in Discrete-Continuous Domains](https://mlsanity.com/paper/2303.04660/) (2023)
- [Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing](https://mlsanity.com/paper/2211.07377/) (2022)
- [RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems](https://mlsanity.com/paper/2103.08057/) (2021)
- [Scalable Neural-Probabilistic Answer Set Programming](https://mlsanity.com/paper/2306.08397/) (2023)
- [Partitioned Variational Inference: A Framework for Probabilistic Federated Learning](https://mlsanity.com/paper/2202.12275/) (2022)
- [Automatic variational inference with cascading flows](https://mlsanity.com/paper/2102.04801/) (2021)
- [SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming](https://mlsanity.com/paper/2110.03395/) (2021)
- [LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation](https://mlsanity.com/paper/2411.00773/) (2024)
- [A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots](https://mlsanity.com/paper/2103.08183/) (2021)
- [Automatically Marginalized MCMC in Probabilistic Programming](https://mlsanity.com/paper/2302.00564/) (2023)
- [Probabilistic Programming with Programmable Variational Inference](https://mlsanity.com/paper/2406.15742/) (2024)
- [Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling](https://mlsanity.com/paper/2110.06021/) (2021)
- [Querying Labelled Data with Scenario Programs for Sim-to-Real Validation](https://mlsanity.com/paper/2112.00206/) (2021)
- [Toward an Idiomatic Framework for Cognitive Robotics](https://mlsanity.com/paper/2111.13027/) (2021)
- [Explaining Deep Tractable Probabilistic Models: The sum-product network case](https://mlsanity.com/paper/2110.09778/) (2021)
- [Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectives](https://mlsanity.com/paper/2203.15972/) (2022)
- [Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data](https://mlsanity.com/paper/2508.18244/) (2025)
- [Variational Inference for Category Recommendation in E-Commerce platforms](https://mlsanity.com/paper/2104.07748/) (2021)
- [Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning](https://mlsanity.com/paper/2107.12591/) (2021)
- [On Reinforcement Learning, Effect Handlers, and the State Monad](https://mlsanity.com/paper/2203.15426/) (2022)
- [Push: Concurrent Probabilistic Programming for Bayesian Deep Learning](https://mlsanity.com/paper/2306.06528/) (2023)
- [Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support](https://mlsanity.com/paper/2310.14888/) (2023)
- [Probabilistic Answer Set Programming with Discrete and Continuous Random Variables](https://mlsanity.com/paper/2409.20274/) (2024)

## Abstract (arXiv)

We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning. For flexibility, Edward makes it easy to fit the same model using a variety of composable inference methods, ranging from point estimation to variational inference to MCMC. In addition, Edward can reuse the modeling representation as part of inference, facilitating the design of rich variational models and generative adversarial networks. For efficiency, Edward is integrated into TensorFlow, providing significant speedups over existing probabilistic systems. For example, we show on a benchmark logistic regression task that Edward is at least 35x faster than Stan and 6x faster than PyMC3. Further, Edward incurs no runtime overhead: it is as fast as handwritten TensorFlow.