mlsanityData to 7 Oct 2026

Amortized Bayesian Multilevel Models

arXiv 2408.13230 ↗First posted 23 Aug 2024stat.ML cs.LG stat.COcited by 12

Not on the map. Why?

Abstract (arXiv)

Multilevel models (MLMs) are a central building block of the Bayesian workflow. They enable joint, interpretable modeling of data across hierarchical levels and provide a fully probabilistic quantification of uncertainty. Despite their well-recognized advantages, MLMs pose significant computational challenges, often rendering their estimation and evaluation intractable within reasonable time constraints. Recent advances in simulation-based inference offer promising solutions for addressing complex probabilistic models using deep generative networks. However, the utility and reliability of deep learning methods for estimating Bayesian MLMs remains largely unexplored, especially when compared with gold-standard samplers. To this end, we explore a family of neural network architectures that leverage the probabilistic factorization of multilevel models to facilitate efficient neural network training and subsequent near-instant posterior inference on unseen datasets. We test our method on several real-world case studies and provide comprehensive comparisons to Stan's gold standard sampler, where possible. Finally, we provide an open-source implementation of our methods to stimulate further research in the nascent field of amortized Bayesian inference.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 60 of its 117 references that are in the map. First posted on arXiv 23 Aug 2024.

Builds on

60 of 117 references.

References · 60

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2016Variational Inference: A Review for Statisticianscited by 1,466
  5. 2017Deep Setscited by 1,394
  6. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  7. 2019Neural Spline Flowscited by 590
  8. 2019The frontier of simulation-based inferencecited by 490
  9. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  10. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  11. 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 207
  12. 2021Benchmarking Simulation-Based Inferencecited by 160
38 more
  1. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  2. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  3. 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 118
  4. 2015Practical Bayesian model evaluation using leave-one-out cross-validation and WAICcited by 110
  5. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 97
  6. 2020Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)cited by 91
  7. 2019Rank-normalization, folding, and localization: An improved widehatR for assessing convergence of MCMCcited by 90
  8. 2019NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transportcited by 73
  9. 2020Neural Approximate Sufficient Statistics for Implicit Modelscited by 72
  10. 2024All-in-one simulation-based inferencecited by 71
  11. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
  12. 2018Mining gold from implicit models to improve likelihood-free inferencecited by 60
  13. 2018Yes, but Did It Work?: Evaluating Variational Inferencecited by 52
  14. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  15. 2021Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networkscited by 48
  16. 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
  17. 2020Bayesian Workflowcited by 47
  18. 2022Compositional Score Modeling for Simulation-based Inferencecited by 46
  19. 2017Sparsity information and regularization in the horseshoe and other shrinkage priorscited by 43
  20. 2015Pareto Smoothed Importance Samplingcited by 42
  21. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  22. 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
  23. 2016Inference Compilation and Universal Probabilistic Programmingcited by 31
  24. 2021Graphical Test for Discrete Uniformity and its Applications in Goodness of Fit Evaluation and Multiple Sample Comparisoncited by 26
  25. 2021Pathfinder: Parallel quasi-Newton variational inferencecited by 26
  26. 2017Visualization in Bayesian workflowcited by 25
  27. 2021Benchmarking Invertible Architectures on Inverse Problemscited by 25
  28. 2016Deep Amortized Inference for Probabilistic Programscited by 22
  29. 2020Amortized Bayesian model comparison with evidential deep learningcited by 22
  30. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  31. 2021Amortized Variational Inference for Simple Hierarchical Modelscited by 19
  32. 2022Simulation-Based Calibration Checking for Bayesian Computation: The Choice of Test Quantities Shapes Sensitivitycited by 19
  33. 2020OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germanycited by 17
  34. 2021HNPE: Leveraging Global Parameters for Neural Posterior Estimationcited by 17
  35. 2022Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomycited by 16
  36. 2016Bayesian Computing with INLA: A Reviewcited by 14
  37. 2021Bayesian hierarchical stacking: Some models are (somewhere) usefulcited by 14
  38. 2023Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inferencecited by 14

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 7.

12 papers.

  1. 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Datacited by 11
  2. 2026BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Pythoncited by 7
  3. 2025Improving the Accuracy of Amortized Model Comparison with Self-Consistencycited by 5
  4. 2025Amortized Bayesian Mixture Modelscited by 3
  5. 2026From Mice to Trains: Amortized Bayesian Inference on Graph Datacited by 2
  6. 2025metabeta -- A fast neural model for Bayesian mixed-effects regressioncited by 1
  7. 2025Improving the Accuracy of Amortized Model Comparison with Self-Consistencycited by 0
  8. 2026Unsupervised Continual Learning for Amortized Bayesian Inferencecited by 0
  9. 2026Tokenised Flow Matching for Hierarchical Simulation Based Inferencecited by 0
  10. 2026Mixed neural posterior estimation for simulators with discrete and continuous parameterscited by 0
  11. 2026High-Dimensional Simulation-Based Inference in Latent Spacescited by 0
  12. 2026Amortized Bayesian Inference on Multilevel Models of Arbitrary Structurecited by 0