mlsanityData to 7 Oct 2026

Pyro: Deep Universal Probabilistic Programming

arXiv 1810.09538 ↗First posted 18 Oct 2018cs.LG cs.PL stat.MLcited by 379

Not on the map. Why?

Abstract (arXiv)

Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research. To scale to large datasets and high-dimensional models, Pyro uses stochastic variational inference algorithms and probability distributions built on top of PyTorch, a modern GPU-accelerated deep learning framework. To accommodate complex or model-specific algorithmic behavior, Pyro leverages Poutine, a library of composable building blocks for modifying the behavior of probabilistic programs.

Key facts. Cited by 379 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 67; 2022: 68; 2023: 82; 2024: 58; 2025: 64; 2026: 39.

379 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2021Transformers Can Do Bayesian Inferencecited by 338
  3. 2021Benchmarking Simulation-Based Inferencecited by 160
  4. 2021High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspacescited by 139
  5. 2022Language Model Cascadescited by 104
  6. 2021Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Designcited by 103
  7. 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 94
  8. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 88
  9. 2024Vanilla Bayesian Optimization Performs Great in High Dimensionscited by 87
  10. 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Expertscited by 85
  11. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  12. 2024Building Machines that Learn and Think with Peoplecited by 73
38 more
  1. 2023Scallop: A Language for Neurosymbolic Programmingcited by 63
  2. 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
  3. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  4. 2021Comparing Test Sets with Item Response Theorycited by 55
  5. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  6. 2022Inferring Rewards from Language in Contextcited by 50
  7. 2022Criteria for Classifying Forecasting Methodscited by 48
  8. 2022A survey of multimodal deep generative modelscited by 47
  9. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  10. 2022Optimizing Sequential Experimental Design with Deep Reinforcement Learningcited by 45
  11. 2022Robust Neural Posterior Estimation and Statistical Model Criticismcited by 45
  12. 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 44
  13. 2022Variational methods for simulation-based inferencecited by 43
  14. 2023Counterfactual Identifiability of Bijective Causal Modelscited by 42
  15. 2021Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibrationcited by 40
  16. 2022NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easycited by 36
  17. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  18. 2023CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulationcited by 33
  19. 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
  20. 2022Tensor Program Optimization with Probabilistic Programscited by 30
  21. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  22. 2022Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Spacecited by 28
  23. 2021Pathfinder: Parallel quasi-Newton variational inferencecited by 26
  24. 2022Bayesian Active Learning with Fully Bayesian Gaussian Processescited by 26
  25. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
  26. 2022Stochastic Causal Programming for Bounding Treatment Effectscited by 25
  27. 2023Neural Probabilistic Logic Programming in Discrete-Continuous Domainscited by 24
  28. 2024BlackJAX: Composable Bayesian inference in JAXcited by 24
  29. 2021Pulling back information geometrycited by 23
  30. 2024sbi reloaded: a toolkit for simulation-based inference workflowscited by 23
  31. 2022Sparse Graph Learning from Spatiotemporal Time Seriescited by 22
  32. 2023Self-Correcting Bayesian Optimization through Bayesian Active Learningcited by 22
  33. 2023On the Convergence of Black-Box Variational Inferencecited by 22
  34. 2024Batch and match: black-box variational inference with a score-based divergencecited by 22
  35. 2024Amortized Probabilistic Conditioning for Optimization, Simulation and Inferencecited by 22
  36. 2021A Structural Causal Model for MR Images of Multiple Sclerosiscited by 21
  37. 2021RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystemscited by 21
  38. 2021The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspectivecited by 21

50 most cited of 379 All 379 (JSON)