mlsanityData to 7 Oct 2026

Deep Probabilistic Programming

arXiv 1701.03757 ↗First posted 13 Jan 2017stat.ML cs.AI cs.LGcited by 24

Not on the map. Why?

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.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 4; 2023: 5; 2024: 3; 2025: 1.

24 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2022Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computingcited by 24
  3. 2023Neural Probabilistic Logic Programming in Discrete-Continuous Domainscited by 24
  4. 2021RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystemscited by 21
  5. 2023Scalable Neural-Probabilistic Answer Set Programmingcited by 14
  6. 2022Partitioned Variational Inference: A Framework for Probabilistic Federated Learningcited by 13
  7. 2021Automatic variational inference with cascading flowscited by 9
  8. 2021SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programmingcited by 8
  9. 2024LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulationcited by 8
  10. 2021A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robotscited by 4
  11. 2023Automatically Marginalized MCMC in Probabilistic Programmingcited by 4
  12. 2024Probabilistic Programming with Programmable Variational Inferencecited by 4
12 more
  1. 2021Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modelingcited by 3
  2. 2021Querying Labelled Data with Scenario Programs for Sim-to-Real Validationcited by 3
  3. 2021Toward an Idiomatic Framework for Cognitive Roboticscited by 2
  4. 2021Explaining Deep Tractable Probabilistic Models: The sum-product network casecited by 1
  5. 2022Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectivescited by 1
  6. 2025Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Datacited by 1
  7. 2021Variational Inference for Category Recommendation in E-Commerce platformscited by 0
  8. 2021Combining Probabilistic Logic and Deep Learning for Self-Supervised Learningcited by 0
  9. 2022On Reinforcement Learning, Effect Handlers, and the State Monadcited by 0
  10. 2023Push: Concurrent Probabilistic Programming for Bayesian Deep Learningcited by 0
  11. 2023Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Supportcited by 0
  12. 2024Probabilistic Answer Set Programming with Discrete and Continuous Random Variablescited by 0