mlsanityData to 7 Oct 2026

JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models

arXiv 2302.09125 ↗First posted 17 Feb 2023cs.LG stat.MLcited by 41

Not on the map. Why?

Abstract (arXiv)

This work proposes ``jointly amortized neural approximation'' (JANA) of intractable likelihood functions and posterior densities arising in Bayesian surrogate modeling and simulation-based inference. We train three complementary networks in an end-to-end fashion: 1) a summary network to compress individual data points, sets, or time series into informative embedding vectors; 2) a posterior network to learn an amortized approximate posterior; and 3) a likelihood network to learn an amortized approximate likelihood. Their interaction opens a new route to amortized marginal likelihood and posterior predictive estimation -- two important ingredients of Bayesian workflows that are often too expensive for standard methods. We benchmark the fidelity of JANA on a variety of simulation models against state-of-the-art Bayesian methods and propose a powerful and interpretable diagnostic for joint calibration. In addition, we investigate the ability of recurrent likelihood networks to emulate complex time series models without resorting to hand-crafted summary statistics.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 41 of its 77 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

41 of 77 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  4. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  5. 2019Neural Spline Flowscited by 590
  6. 2019The frontier of simulation-based inferencecited by 490
  7. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  8. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  9. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  10. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  11. 2021Benchmarking Simulation-Based Inferencecited by 160
  12. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
29 more
  1. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  2. 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 118
  3. 2015Practical Bayesian model evaluation using leave-one-out cross-validation and WAICcited by 110
  4. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 97
  5. 2020On Contrastive Learning for Likelihood-free Inferencecited by 96
  6. 2020Neural Approximate Sufficient Statistics for Implicit Modelscited by 72
  7. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
  8. 2015Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Modelscited by 61
  9. 2018Likelihood-free inference with emulator networkscited by 61
  10. 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
  11. 2021Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networkscited by 48
  12. 2022Variational methods for simulation-based inferencecited by 43
  13. 2022Truncated proposals for scalable and hassle-free simulation-based inferencecited by 40
  14. 2015Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Networkcited by 39
  15. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  16. 2021Sequential Neural Posterior and Likelihood Approximationcited by 30
  17. 2021A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithfulcited by 27
  18. 2021Graphical Test for Discrete Uniformity and its Applications in Goodness of Fit Evaluation and Multiple Sample Comparisoncited by 26
  19. 2020Amortized Bayesian model comparison with evidential deep learningcited by 22
  20. 2020Score Matched Neural Exponential Families for Likelihood-Free Inferencecited by 21
  21. 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
  22. 2021Understanding Event-Generation Networks via Uncertaintiescited by 17
  23. 2019Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computationcited by 12
  24. 2020Robust model training and generalisation with Studentising flowscited by 10
  25. 2022Whitening Convergence Rate of Coupling-based Normalizing Flowscited by 6
  26. 2019Probabilistic Surrogate Networks for Simulators with Unbounded Randomnesscited by 4
  27. 2015Likelihood-free Model Choicecited by 3
  28. 2018Efficient leave-one-out cross-validation for Bayesian non-factorized normal and Student-t modelscited by 3
  29. 2022Guided sequential ABC schemes for intractable Bayesian modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 10; 2025: 14; 2026: 7.

41 papers.

Sort:

By area:

  1. 2024All-in-one simulation-based inferencecited by 71
  2. 2024Neural Methods for Amortized Inferencecited by 36
  3. 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
  4. 2025Simulation-Based Inference: A Practical Guidecited by 30
  5. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  6. 2024Amortized Probabilistic Conditioning for Optimization, Simulation and Inferencecited by 22
  7. 2023Sensitivity-Aware Amortized Bayesian Inferencecited by 20
  8. 2023Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inferencecited by 14
  9. 2023Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networkscited by 13
  10. 2025Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Modelscited by 13
  11. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 12
  12. 2024Amortized Bayesian Multilevel Modelscited by 12
29 more
  1. 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Datacited by 11
  2. 2023Simulation-based Inference for High-dimensional Data using Surjective Sequential Neural Likelihood Estimationcited by 8
  3. 2024Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigationcited by 8
  4. 2024Compositional simulation-based inference for time seriescited by 8
  5. 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisitioncited by 8
  6. 2026BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Pythoncited by 7
  7. 2025Multilevel neural simulation-based inferencecited by 5
  8. 2025Improving the Accuracy of Amortized Model Comparison with Self-Consistencycited by 5
  9. 2023Uncertainty Quantification and Propagation in Surrogate-based Bayesian Inferencecited by 4
  10. 2023Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inferencecited by 3
  11. 2024Fast, accurate and lightweight sequential simulation-based inference using Gaussian locally linear mappingscited by 3
  12. 2024Demonstrating the power and flexibility of variational assumptions for amortized neural posterior estimation in environmental applicationscited by 3
  13. 2025All Emulators are Wrong, Many are Useful, and Some are More Useful Than Others: A Reproducible Comparison of Computer Model Surrogatescited by 3
  14. 2024Variational Autoencoders for Efficient Simulation-Based Inferencecited by 2
  15. 2025Simulation-based inference for stochastic nonlinear mixed-effects models with applications in systems biologycited by 2
  16. 2025ConDiSim: Conditional Diffusion Models for Simulation Based Inferencecited by 2
  17. 2026From Mice to Trains: Amortized Bayesian Inference on Graph Datacited by 2
  18. 2023Goal-oriented Uncertainty Quantification for Inverse Problems via Variational Encoder-Decoder Networkscited by 1
  19. 2024Mixed Noise and Posterior Estimation with Conditional DeepGEMcited by 1
  20. 2025Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Modelscited by 1
  21. 2025Causal Posterior Estimationcited by 1
  22. 2025Trustworthy scientific inference with generative modelscited by 1
  23. 2025An invertible generative model for forward and inverse problemscited by 1
  24. 2026Scalable Simulation-Based Model Inference with Test-Time Complexity Controlcited by 1
  25. 2025Neural Bayes estimation and selection for complex bivariate extremal dependence modelscited by 0
  26. 2026OneFlowSBI: One Model, Many Queries for Simulation-Based Inferencecited by 0
  27. 2026Tokenised Flow Matching for Hierarchical Simulation Based Inferencecited by 0
  28. 2026Amortized Factor Inference Networks for Posterior Inferencecited by 0
  29. 2026Amortized ratio-estimation importance sampling and localized simulation-based calibration for intractable likelihoodscited by 0