mlsanityData to 14 Oct 2026

Rethinking Variational Inference for Probabilistic Programs with Stochastic Support

arXiv 2311.00594 ↗First posted 1 Nov 2023cs.LG cs.AI cs.PLcited by 2

Not on the map. Why?

Abstract (arXiv)

We introduce Support Decomposition Variational Inference (SDVI), a new variational inference (VI) approach for probabilistic programs with stochastic support. Existing approaches to this problem rely on designing a single global variational guide on a variable-by-variable basis, while maintaining the stochastic control flow of the original program. SDVI instead breaks the program down into sub-programs with static support, before automatically building separate sub-guides for each. This decomposition significantly aids in the construction of suitable variational families, enabling, in turn, substantial improvements in inference performance.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 71 references that are in the map. First posted on arXiv 1 Nov 2023.

Builds on

38 of 71 references.

References · 38

  1. 2015Variational Inference with Normalizing Flowscited by 2,170
  2. 2016Variational Inference: A Review for Statisticianscited by 1,472
  3. 2015Automatic differentiation in machine learning: a surveycited by 855
  4. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  5. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 470
  6. 2018Pyro: Deep Universal Probabilistic Programmingcited by 380
  7. 2013Black Box Variational Inferencecited by 319
  8. 2019Monte Carlo Gradient Estimation in Machine Learningcited by 283
  9. 2017Advances in Variational Inferencecited by 236
  10. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  11. 2016Automatic Differentiation Variational Inferencecited by 159
  12. 2013Structure Discovery in Nonparametric Regression through Compositional Kernel Searchcited by 88
26 more
  1. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  2. 2018An Introduction to Probabilistic Programmingcited by 63
  3. 2020Markovian Score Climbing: Variational Inference with KL(p||q)cited by 46
  4. 2020Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimizationcited by 37
  5. 2021Challenges and Opportunities in High-dimensional Variational Inferencecited by 35
  6. 2013Automated Variational Inference in Probabilistic Programmingcited by 34
  7. 2016Inference Compilation and Universal Probabilistic Programmingcited by 32
  8. 2017Faithful Inversion of Generative Models for Effective Amortized Inferencecited by 29
  9. 2015Automatic Variational Inference in Stancited by 24
  10. 2015A New Approach to Probabilistic Programming Inferencecited by 22
  11. 2020Automatic structured variational inferencecited by 22
  12. 2014Venture: a higher-order probabilistic programming platform with programmable inferencecited by 20
  13. 2016Inference Networks for Sequential Monte Carlo in Graphical Modelscited by 20
  14. 2015Layered Adaptive Importance Samplingcited by 18
  15. 2019Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scalecited by 18
  16. 2016Design and Implementation of Probabilistic Programming Language Anglicancited by 15
  17. 2018Reparameterization Gradient for Non-differentiable Modelscited by 11
  18. 2018Automated learning with a probabilistic programming language: Birchcited by 11
  19. 2019Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Supportcited by 11
  20. 2016Interacting Particle Markov Chain Monte Carlocited by 6
  21. 2015Black-Box Policy Search with Probabilistic Programscited by 4
  22. 2021Nonparametric Hamiltonian Monte Carlocited by 4
  23. 2014A Compilation Target for Probabilistic Programming Languagescited by 3
  24. 2019Hijacking Malaria Simulators with Probabilistic Programmingcited by 3
  25. 2019Attention for Inference Compilationcited by 3
  26. 2022Guaranteed Bounds for Posterior Inference in Universal Probabilistic Programmingcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Understanding and mitigating difficulties in posterior predictive evaluationcited by 1
  2. 2025Variational Task Vector Compositioncited by 0