mlsanityData to 7 Oct 2026

Preconditioned Neural Posterior Estimation for Likelihood-free Inference

arXiv 2404.13557 ↗First posted 21 Apr 2024stat.ML cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Simulation based inference (SBI) methods enable the estimation of posterior distributions when the likelihood function is intractable, but where model simulation is feasible. Popular neural approaches to SBI are the neural posterior estimator (NPE) and its sequential version (SNPE). These methods can outperform statistical SBI approaches such as approximate Bayesian computation (ABC), particularly for relatively small numbers of model simulations. However, we show in this paper that the NPE methods are not guaranteed to be highly accurate, even on problems with low dimension. In such settings the posterior cannot be accurately trained over the prior predictive space, and even the sequential extension remains sub-optimal. To overcome this, we propose preconditioned NPE (PNPE) and its sequential version (PSNPE), which uses a short run of ABC to effectively eliminate regions of parameter space that produce large discrepancy between simulations and data and allow the posterior emulator to be more accurately trained. We present comprehensive empirical evidence that this melding of neural and statistical SBI methods improves performance over a range of examples, including a motivating example involving a complex agent-based model applied to real tumour growth data.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 31 of its 64 references that are in the map. First posted on arXiv 21 Apr 2024.

Builds on

31 of 64 references.

References · 31

  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  3. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  4. 2019Neural Spline Flowscited by 590
  5. 2019The frontier of simulation-based inferencecited by 490
  6. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  7. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  8. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  9. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  10. 2021Benchmarking Simulation-Based Inferencecited by 160
  11. 2021Real-time gravitational-wave science with neural posterior estimationcited by 76
  12. 2021Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networkscited by 48
19 more
  1. 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
  2. 2022Robust Neural Posterior Estimation and Statistical Model Criticismcited by 45
  3. 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 44
  4. 2022Truncated proposals for scalable and hassle-free simulation-based inferencecited by 40
  5. 2015Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Networkcited by 39
  6. 2020Invertible Generative Modeling using Linear Rational Splinescited by 39
  7. 2019Approximate Bayesian computation with the Wasserstein distancecited by 34
  8. 2023Bayesian Synthetic Likelihoodcited by 29
  9. 2023Adversarial robustness of amortized Bayesian inferencecited by 17
  10. 2023Simulation-based Inference for Cardiovascular Modelscited by 11
  11. 2017ELFI: Engine for Likelihood-Free Inferencecited by 10
  12. 2021A Comparison of Likelihood-Free Methods With and Without Summary Statisticscited by 9
  13. 2023Misspecification-robust Sequential Neural Likelihood for Simulation-based Inferencecited by 8
  14. 2020Misspecification-robust likelihood-free inference in high dimensionscited by 4
  15. 2021Inferring dark matter substructure with astrometric lensing beyond the power spectrumcited by 4
  16. 2023Field-level simulation-based inference with galaxy catalogs: the impact of systematic effectscited by 4
  17. 2022Improving the Accuracy of Marginal Approximations in Likelihood-Free Inference via Localisationcited by 2
  18. 2023Fast Parameter Inference on Pulsar Timing Arrays with Normalizing Flowscited by 2
  19. 2022Pooling information in likelihood-free inferencecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  2. 2025Simulation-based Bayesian inference under model misspecificationcited by 9
  3. 2024Domain-Adaptive Neural Posterior Estimation for Strong Gravitational Lens Analysiscited by 7
  4. 2024A Comprehensive Guide to Simulation-based Inference in Computational Biologycited by 5
  5. 2026Preconditioned Robust Neural Posterior Estimation for Misspecified Simulatorscited by 0
  6. 2026Identifiability and amortized inference limitations in Kuramoto modelscited by 0