mlsanityData to 7 Oct 2026

Consistency Models for Scalable and Fast Simulation-Based Inference

arXiv 2312.05440 ↗First posted 9 Dec 2023cs.LG cs.AI stat.MLcited by 22

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Simulation-based inference (SBI) is constantly in search of more expressive and efficient algorithms to accurately infer the parameters of complex simulation models. In line with this goal, we present consistency models for posterior estimation (CMPE), a new conditional sampler for SBI that inherits the advantages of recent unconstrained architectures and overcomes their sampling inefficiency at inference time. CMPE essentially distills a continuous probability flow and enables rapid few-shot inference with an unconstrained architecture that can be flexibly tailored to the structure of the estimation problem. We provide hyperparameters and default architectures that support consistency training over a wide range of different dimensions, including low-dimensional ones which are important in SBI workflows but were previously difficult to tackle even with unconditional consistency models. Our empirical evaluation demonstrates that CMPE not only outperforms current state-of-the-art algorithms on hard low-dimensional benchmarks, but also achieves competitive performance with much faster sampling speed on two realistic estimation problems with high data and/or parameter dimensions.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 49 of its 73 references that are in the map. First posted on arXiv 9 Dec 2023.

Builds on

49 of 73 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Flow Matching for Scalable Simulation-Based Inference26 May
  2. 2022Flow Matching for Generative Modeling6 Oct

Other references · 47

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2016Density estimation using Real NVPcited by 2,029
  10. 2023Consistency Modelscited by 1,778
  11. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  12. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
35 more
  1. 2018Computational Optimal Transportcited by 765
  2. 2019Neural Spline Flowscited by 590
  3. 2019The frontier of simulation-based inferencecited by 490
  4. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  5. 2023Improved Techniques for Training Consistency Modelscited by 430
  6. 2016Generating Videos with Scene Dynamicscited by 376
  7. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  8. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  9. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 195
  10. 2020DDSP: Differentiable Digital Signal Processingcited by 177
  11. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  12. 2021Benchmarking Simulation-Based Inferencecited by 160
  13. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  14. 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 118
  15. 2020On Contrastive Learning for Likelihood-free Inferencecited by 96
  16. 2021Real-time gravitational-wave science with neural posterior estimationcited by 76
  17. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
  18. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  19. 2019Statistical Inference for Generative Models with Maximum Mean Discrepancycited by 43
  20. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  21. 2022Truncated proposals for scalable and hassle-free simulation-based inferencecited by 40
  22. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  23. 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
  24. 2021Sequential Neural Posterior and Likelihood Approximationcited by 30
  25. 2022Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inferencecited by 28
  26. 2021Benchmarking Invertible Architectures on Inverse Problemscited by 25
  27. 2020Amortized Bayesian model comparison with evidential deep learningcited by 22
  28. 2020Score Matched Neural Exponential Families for Likelihood-Free Inferencecited by 21
  29. 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
  30. 2022Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomycited by 16
  31. 2023Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inferencecited by 14
  32. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 12
  33. 2023A Deep Learning Method for Comparing Bayesian Hierarchical Modelscited by 11
  34. 2023Simultaneous identification of models and parameters of scientific simulatorscited by 8
  35. 2023Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inferencecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 15; 2026: 4.

22 papers.

Sort:

By area:

  1. 2025Simulation-Based Inference: A Practical Guidecited by 30
  2. 2024Amortized Bayesian Multilevel Modelscited by 12
  3. 2025Multifidelity Simulation-based Inference for Computationally Expensive Simulatorscited by 9
  4. 2026BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Pythoncited by 7
  5. 2024Simulation-based Inference with the Python Package sbijaxcited by 5
  6. 2025Multilevel neural simulation-based inferencecited by 5
  7. 2024Amortized Bayesian Workflowcited by 3
  8. 2025Amortized Bayesian Mixture Modelscited by 3
  9. 2025Posterior SBC: Simulation-Based Calibration Checking Conditional on Datacited by 3
  10. 2025FNOPE: Simulation-based inference on function spaces with Fourier Neural Operatorscited by 3
  11. 2025ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matchingcited by 3
  12. 2025PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inferencecited by 3
10 more
  1. 2025JADAI: Jointly Amortizing Adaptive Design and Bayesian Inferencecited by 2
  2. 2025Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Modelscited by 1
  3. 2025Causal Posterior Estimationcited by 1
  4. 2025Trustworthy scientific inference with generative modelscited by 1
  5. 2025A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarioscited by 1
  6. 2026An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learningcited by 1
  7. 2025Recent Advances in Simulation-based Inference for Gravitational Wave Data Analysiscited by 0
  8. 2025Policy-Driven AI in Dataspaces: Taxonomy, Explainability, and Pathways for Compliant Innovationcited by 0
  9. 2026Conservative neural posterior estimation via distributionally robust trainingcited by 0
  10. 2026High-Dimensional Simulation-Based Inference in Latent Spacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Flow Matching Calibration for Simulation-Based Inference under Model Misspecification
  2. 2026Tokenised Flow Matching for Hierarchical Simulation Based Inference
  3. 2026Spectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based Inference
  4. 2025Improving the Accuracy of Amortized Model Comparison with Self-Consistency
  5. 2026Amortized ratio-estimation importance sampling and localized simulation-based calibration for intractable likelihoods
  6. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Review
  7. 2025CP4SBI: Local Conformal Calibration of Credible Sets in Simulation-Based Inference
  8. 2026Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference