mlsanityData to 14 Oct 2026

Multilevel neural simulation-based inference

arXiv 2506.06087 ↗First posted 6 Jun 2025stat.ML astro-ph.CO astro-ph.IMcited by 5

Not on the map. Why?

Abstract (arXiv)

Neural simulation-based inference (SBI) is a popular set of methods for Bayesian inference when models are only available in the form of a simulator. These methods are widely used in the sciences and engineering, where writing down a likelihood can be significantly more challenging than constructing a simulator. However, the performance of neural SBI can suffer when simulators are computationally expensive, thereby limiting the number of simulations that can be performed. In this paper, we propose a novel approach to neural SBI which leverages multilevel Monte Carlo techniques for settings where several simulators of varying cost and fidelity are available. We demonstrate through both theoretical analysis and extensive experiments that our method can significantly enhance the accuracy of SBI methods given a fixed computational budget.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 51 of its 103 references that are in the map. First posted on arXiv 6 Jun 2025.

Builds on

51 of 103 references.

References · 51

  1. 2015Variational Inference with Normalizing Flowscited by 2,170
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  3. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  5. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  6. 2019Neural Spline Flowscited by 596
  7. 2019The frontier of simulation-based inferencecited by 502
  8. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 221
  9. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 219
  10. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 163
  11. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 144
  12. 2018Survey of multifidelity methods in uncertainty propagation, inference, and optimizationcited by 142
38 more
  1. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 101
  2. 2020On Contrastive Learning for Likelihood-free Inferencecited by 98
  3. 2016Likelihood-free inference by ratio estimationcited by 81
  4. 2024All-in-one simulation-based inferencecited by 74
  5. 2015Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Modelscited by 61
  6. 2018Likelihood-free inference with emulator networkscited by 61
  7. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  8. 2022Compositional Score Modeling for Simulation-based Inferencecited by 48
  9. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  10. 2024Neural Methods for Amortized Inferencecited by 39
  11. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  12. 2023BayesFlow: Amortized Bayesian Workflows With Neural Networkscited by 32
  13. 2023Bayesian Synthetic Likelihoodcited by 29
  14. 2021Stochastic Bias-Reduced Gradient Methodscited by 25
  15. 2020Solving high-dimensional parameter inference: marginal posterior densities & Moment Networkscited by 22
  16. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  17. 2020Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designscited by 19
  18. 2014GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computationcited by 17
  19. 2021Composite Goodness-of-fit Tests with Kernelscited by 16
  20. 2019Multilevel Monte Carlo Variational Inferencecited by 15
  21. 2023Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inferencecited by 14
  22. 2023Contextual Stochastic Bilevel Optimizationcited by 14
  23. 2018Multilevel Monte Carlo estimation of expected information gainscited by 13
  24. 2023Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inferencecited by 13
  25. 2021Discrepancy-based Inference for Intractable Generative Models using Quasi-Monte Carlocited by 12
  26. 2022Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flowscited by 11
  27. 2020A General Method for Calibrating Stochastic Radio Channel Models with Kernelscited by 9
  28. 2022Approximate Bayesian Computation with Domain Expert in the Loopcited by 9
  29. 2024Compositional simulation-based inference for time seriescited by 9
  30. 2025Multifidelity Simulation-based Inference for Computationally Expensive Simulatorscited by 9
  31. 2022Multilevel Bayesian Quadraturecited by 8
  32. 2025Bifidelity Parameter Estimation Using Conditional Diffusion Modelscited by 7
  33. 2022The CAMELS project: public data releasecited by 6
  34. 2024Cost-aware simulation-based inferencecited by 6
  35. 2025Nested Expectations with Kernel Quadraturecited by 5
  36. 2024Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Needcited by 4
  37. 2025Transfer learning for multifidelity simulation-based inference in cosmologycited by 4
  38. 2017Multilevel Monte Carlo in Approximate Bayesian Computationcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Simulation-Based Empirical Bayescited by 1
  2. 2025Transfer Learning Beyond the Standard Modelcited by 0
  3. 2026Multi-level Monte Carlo Dropout for Efficient Uncertainty Quantificationcited by 0
  4. 2026Conservative neural posterior estimation via distributionally robust trainingcited by 0
  5. 2026A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problemscited by 0