mlsanityData to 7 Oct 2026

Neural Methods for Amortized Inference

arXiv 2404.12484 ↗First posted 18 Apr 2024stat.ML cs.LG stat.COcited by 36

Not on the map. Why?

Abstract (arXiv)

Simulation-based methods for statistical inference have evolved dramatically over the past 50 years, keeping pace with technological advancements. The field is undergoing a new revolution as it embraces the representational capacity of neural networks, optimization libraries and graphics processing units for learning complex mappings between data and inferential targets. The resulting tools are amortized, in the sense that, after an initial setup cost, they allow rapid inference through fast feed-forward operations. In this article we review recent progress in the context of point estimation, approximate Bayesian inference, summary-statistic construction, and likelihood approximation. We also cover software, and include a simple illustration to showcase the wide array of tools available for amortized inference and the benefits they offer over Markov chain Monte Carlo methods. The article concludes with an overview of relevant topics and an outlook on future research directions.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 89 of its 162 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

89 of 162 references.

References · 89

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  8. 2017Deep Setscited by 1,394
  9. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  11. 2019An Introduction to Variational Autoencoderscited by 997
  12. 2017Masked Autoregressive Flow for Density Estimationcited by 680
38 more
  1. 2018MINE: Mutual Information Neural Estimationcited by 680
  2. 2019The frontier of simulation-based inferencecited by 490
  3. 2016Tutorial on Variational Autoencoderscited by 404
  4. 2022Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Modelcited by 264
  5. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  6. 2017Advances in Variational Inferencecited by 236
  7. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  8. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  9. 2013A General Framework for Updating Belief Distributionscited by 172
  10. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  11. 2021Benchmarking Simulation-Based Inferencecited by 160
  12. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  13. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  14. 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 118
  15. 2014Neural Variational Inference and Learning in Belief Networkscited by 116
  16. 2017Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledgecited by 95
  17. 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 87
  18. 2018Semi-Amortized Variational Autoencoderscited by 83
  19. 2016Likelihood-free inference by ratio estimationcited by 80
  20. 2020Neural Approximate Sufficient Statistics for Implicit Modelscited by 72
  21. 2024All-in-one simulation-based inferencecited by 71
  22. 2017A general framework for Vecchia approximations of Gaussian processescited by 66
  23. 2018Likelihood-free inference with emulator networkscited by 61
  24. 2018Mining gold from implicit models to improve likelihood-free inferencecited by 60
  25. 2021Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networkscited by 48
  26. 2022Variational methods for simulation-based inferencecited by 43
  27. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  28. 2015Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Networkcited by 39
  29. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  30. 2019Solving Bayesian Inverse Problems via Variational Autoencoderscited by 32
  31. 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
  32. 2019HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inferencecited by 31
  33. 2022Likelihood-Free Parameter Estimation with Neural Bayes Estimatorscited by 31
  34. 2018A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networkscited by 30
  35. 2021Sequential Neural Posterior and Likelihood Approximationcited by 30
  36. 2021Truncated Marginal Neural Ratio Estimationcited by 30
  37. 2021Neural Networks for Parameter Estimation in Intractable Modelscited by 28
  38. 2023Amortized Variational Inference: When and Why?cited by 28

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 17; 2026: 14.

36 papers.

Sort:

By area:

  1. 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Datacited by 11
  2. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  3. 2025Simulation-based Bayesian inference under model misspecificationcited by 9
  4. 2025Solving Empirical Bayes via Transformerscited by 7
  5. 2025Bifidelity Parameter Estimation Using Conditional Diffusion Modelscited by 7
  6. 2026BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Pythoncited by 7
  7. 2025Multilevel neural simulation-based inferencecited by 5
  8. 2024Generative Bayesian Computation for Maximum Expected Utilitycited by 3
  9. 2024Amortized Bayesian Workflowcited by 3
  10. 2025Posterior SBC: Simulation-Based Calibration Checking Conditional on Datacited by 3
  11. 2025Simulation-based inference for stochastic nonlinear mixed-effects models with applications in systems biologycited by 2
  12. 2025ConDiSim: Conditional Diffusion Models for Simulation Based Inferencecited by 2
24 more
  1. 2025Variational Transdimensional Inferencecited by 2
  2. 2025JADAI: Jointly Amortizing Adaptive Design and Bayesian Inferencecited by 2
  3. 2026Error Analysis of Bayesian Inverse Problems with Generative Priorscited by 2
  4. 2026Amortized Filtering and Smoothing with Conditional Normalizing Flowscited by 2
  5. 2025Modeling Spatial Extremes using Non-Gaussian Spatial Autoregressive Models via Convolutional Neural Networkscited by 1
  6. 2025LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Datacited by 1
  7. 2025Theoretical guarantees for neural estimators in parametric statisticscited by 1
  8. 2026LatentFlow: A General Framework for Conditioning Stochastic Processescited by 1
  9. 2024Latent Variable Sequence Identification for Cognitive Models with Neural Network Estimatorscited by 0
  10. 2024A Generalized Unified Skew-Normal Process with Neural Bayes Inferencecited by 0
  11. 2024When the whole is greater than the sum of its parts: Scaling black-box inference to large data settings through divide-and-conquercited by 0
  12. 2025Neural Bayes estimation and selection for complex bivariate extremal dependence modelscited by 0
  13. 2025One-shot Conditional Sampling: MMD meets Nearest Neighborscited by 0
  14. 2025A Black-Box Debiasing Framework for Conditional Samplingcited by 0
  15. 2026Neural Architectures for Amortized Bayesian Inference: Statistical Foundations and Empirical Assessmentscited by 0
  16. 2026Universal priors: solving empirical Bayes via Bayesian inference and pretrainingcited by 0
  17. 2026Unsupervised Continual Learning for Amortized Bayesian Inferencecited by 0
  18. 2026Improving moment tensor solutions under Earth structure uncertainty with simulation-based inferencecited by 0
  19. 2026Identifiability and amortized inference limitations in Kuramoto modelscited by 0
  20. 2026Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimationcited by 0
  21. 2026Amortized Inference for Sampling Distributions Where the Bootstrap Failscited by 0
  22. 2026Self-Augmented Diffusion Guidance for Physics-Informed Generationcited by 0
  23. 2026Simulation-Based Quantum System Inference with Neural Posterior Estimationcited by 0
  24. 2026Amortized Bayesian Inference on Multilevel Models of Arbitrary Structurecited by 0