mlsanityData to 7 Oct 2026

Automatically Marginalized MCMC in Probabilistic Programming

arXiv 2302.00564 ↗First posted 1 Feb 2023cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Hamiltonian Monte Carlo (HMC) is a powerful algorithm to sample latent variables from Bayesian models. The advent of probabilistic programming languages (PPLs) frees users from writing inference algorithms and lets users focus on modeling. However, many models are difficult for HMC to solve directly, and often require tricks like model reparameterization. We are motivated by the fact that many of those models could be simplified by marginalization. We propose to use automatic marginalization as part of the sampling process using HMC in a graphical model extracted from a PPL, which substantially improves sampling from real-world hierarchical models.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 57 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

24 of 57 references.

References · 24

  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  3. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  4. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 187
  5. 2016Automatic Differentiation Variational Inferencecited by 159
  6. 2019NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transportcited by 73
  7. 2018An Introduction to Probabilistic Programmingcited by 62
  8. 2013Hamiltonian Monte Carlo for Hierarchical Modelscited by 50
  9. 2013Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networkscited by 46
  10. 2017Deep Probabilistic Programmingcited by 24
  11. 2015A New Approach to Probabilistic Programming Inferencecited by 22
  12. 2020Involutive MCMC: a Unifying Frameworkcited by 19
12 more
  1. 2019Automatic Reparameterisation of Probabilistic Programscited by 18
  2. 2018Automated learning with a probabilistic programming language: Birchcited by 11
  3. 2017Delayed Sampling and Automatic Rao-Blackwellization of Probabilistic Programscited by 8
  4. 2019Reactive Probabilistic Programmingcited by 6
  5. 2019Functional Tensors for Probabilistic Programmingcited by 6
  6. 2019Tensor Variable Elimination for Plated Factor Graphscited by 5
  7. 2020Conditional independence by typingcited by 5
  8. 2022Semi-Symbolic Inference for Efficient Streaming Probabilistic Programmingcited by 5
  9. 2018Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Languagecited by 4
  10. 2020Joint Distributions for TensorFlow Probabilitycited by 4
  11. 2022Program Analysis of Probabilistic Programscited by 1
  12. 2022Nonparametric Involutive Markov Chain Monte Carlocited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2024Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Modelscited by 1
  2. 2023Push: Concurrent Probabilistic Programming for Bayesian Deep Learningcited by 0
  3. 2024Inference Plans for Hybrid Particle Filteringcited by 0
  4. 2026Automatic Laplace Collapsed Sampling: Scalable Marginalisation of Latent Parameters via Automatic Differentiationcited by 0