Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrap
Not on the map. Why?
Abstract (arXiv)
Simulator-based models are models for which the likelihood is intractable but simulation of synthetic data is possible. They are often used to describe complex real-world phenomena, and as such can often be misspecified in practice. Unfortunately, existing Bayesian approaches for simulators are known to perform poorly in those cases. In this paper, we propose a novel algorithm based on the posterior bootstrap and maximum mean discrepancy estimators. This leads to a highly-parallelisable Bayesian inference algorithm with strong robustness properties. This is demonstrated through an in-depth theoretical study which includes generalisation bounds and proofs of frequentist consistency and robustness of our posterior. The approach is then assessed on a range of examples including a g-and-k distribution and a toggle-switch model.
Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 33 of its 85 references that are in the map. First posted on arXiv 9 Feb 2022.
Builds on
33 of 85 references.
References · 33
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019The frontier of simulation-based inferencecited by 490
- 2015Generative Moment Matching Networkscited by 252
- 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
- 2013A General Framework for Updating Belief Distributionscited by 172
- 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
- 2016Generative Models and Model Criticism via Optimized Maximum Mean Discrepancycited by 99
- 2014Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing Itcited by 92
- 2019Generalized Variational Inference: Three arguments for deriving new Posteriorscited by 57
- 2021Robust Generalised Bayesian Inference for Intractable Likelihoodscited by 53
- 2016Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimationcited by 50
- 2019Statistical Inference for Generative Models with Maximum Mean Discrepancycited by 43
21 more
- 2019MMD-Bayes: Robust Bayesian Estimation via Maximum Mean Discrepancycited by 35
- 2017General Bayesian Updating and the Loss-Likelihood Bootstrapcited by 34
- 2019Approximate Bayesian computation with the Wasserstein distancecited by 34
- 2019Finite sample properties of parametric MMD estimation: robustness to misspecification and dependencecited by 24
- 2020A comparison of learning rate selection methods in generalized Bayesian inferencecited by 23
- 2020Generalized Posteriors in Approximate Bayesian Computationcited by 19
- 2018Nonparametric learning from Bayesian models with randomized objective functionscited by 17
- 2019Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrapcited by 16
- 2021Composite Goodness-of-fit Tests with Kernelscited by 16
- 2021Discrepancy-based Inference for Intractable Generative Models using Quasi-Monte Carlocited by 12
- 2020A General Method for Calibrating Stochastic Radio Channel Models with Kernelscited by 9
- 2017On parameter estimation with the Wasserstein distancecited by 7
- 2019Likelihood-free approximate Gibbs samplingcited by 7
- 2019Focused Bayesian Predictioncited by 6
- 2020Robust Bayesian Inference for Discrete Outcomes with the Total Variation Distancecited by 6
- 2020Misspecification-robust likelihood-free inference in high dimensionscited by 4
- 2016Estimating Quantile Families of Loss Distributions for Non-Life Insurance Modelling via L-momentscited by 3
- 2017Model Misspecification in ABC: Consequences and Diagnosticscited by 3
- 2018ABC Samplerscited by 2
- 2020Generalised Bayes Updates with f-divergences through Probabilistic Classifierscited by 2
- 2021Introducing prior information in Weighted Likelihood Bootstrap with applications to model misspecificationcited by 2
Built on by
Citing papers per year: 2022: 4; 2023: 12; 2024: 7; 2025: 14; 2026: 4.
41 papers.
Sort:
- 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
- 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 44
- 2022Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimationcited by 27
- 2024Addressing Misspecification in Simulation-based Inference through Data-driven Calibrationcited by 26
- 2023Sensitivity-Aware Amortized Bayesian Inferencecited by 20
- 2023Adversarial robustness of amortized Bayesian inferencecited by 17
- 2023Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimationcited by 17
- 2023Robust and Scalable Bayesian Online Changepoint Detectioncited by 16
- 2022Targeted Separation and Convergence with Kernel Discrepanciescited by 15
- 2022Generalised Bayesian Inference for Discrete Intractable Likelihoodcited by 14
- 2023Robust and Conjugate Gaussian Process Regressioncited by 14
- 2023Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inferencecited by 13
29 more
- 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Datacited by 11
- 2024Sourcerer: Sample-based Maximum Entropy Source Distribution Estimationcited by 9
- 2025Simulation-based Bayesian inference under model misspecificationcited by 9
- 2025A Dictionary of Closed-Form Kernel Mean Embeddingscited by 9
- 2023Misspecification-robust Sequential Neural Likelihood for Simulation-based Inferencecited by 8
- 2024Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigationcited by 8
- 2024Robust Kernel Hypothesis Testing under Data Corruptioncited by 7
- 2024On the Robustness of Kernel Goodness-of-Fit Testscited by 7
- 2024Cost-aware simulation-based inferencecited by 6
- 2025TabMGP: Martingale Posterior with TabPFNcited by 6
- 2024A Comprehensive Guide to Simulation-based Inference in Computational Biologycited by 5
- 2025Robust Simulation-Based Inference under Missing Data via Neural Processescited by 5
- 2023A Semi-Bayesian Nonparametric Estimator of the Maximum Mean Discrepancy Measure: Applications in Goodness-of-Fit Testing and Generative Adversarial Networkscited by 3
- 2026Minimum Distance Summaries for Robust Neural Posterior Estimationcited by 3
- 2023Robust Bayesian Inference for Measurement Error Misspecification: The Berkson and Classical Casescited by 2
- 2025SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence eracited by 2
- 2025Decision Making under Model Misspecification: DRO with Robust Bayesian Ambiguity Setscited by 2
- 2023A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancycited by 1
- 2025Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Modelscited by 1
- 2025Causal Posterior Estimationcited by 1
- 2025Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inferencecited by 1
- 2025Multi-Output Robust and Conjugate Gaussian Processescited by 1
- 2025Robust Bayesian Optimisation with Unbounded Corruptionscited by 1
- 2023Pseudo-Likelihood Inferencecited by 0
- 2025A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimationcited by 0
- 2025Misspecification-robust amortised simulation-based inference using variational methodscited by 0
- 2026Unsupervised Continual Learning for Amortized Bayesian Inferencecited by 0
- 2026Variational predictive resamplingcited by 0
- 2026A Gradient Flow Perspective on Minimum MMD Estimationcited by 0
- 2026A Gradient Flow Perspective on Minimum MMD Estimation4 Jul 2026
- 2026Variational predictive resampling11 May 2026
- 2026Unsupervised Continual Learning for Amortized Bayesian Inference26 Feb 2026
- 2026Minimum Distance Summaries for Robust Neural Posterior Estimation9 Feb 2026
- 2025Robust Bayesian Optimisation with Unbounded Corruptions19 Nov 2025
- 2025Multi-Output Robust and Conjugate Gaussian Processes30 Oct 2025
- 2025TabMGP: Martingale Posterior with TabPFN29 Oct 2025
- 2025Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference2 Oct 2025
- 2025Misspecification-robust amortised simulation-based inference using variational methods6 Sep 2025
- 2025Causal Posterior Estimation27 May 2025
- 2025Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Models13 May 2025
- 2025Decision Making under Model Misspecification: DRO with Robust Bayesian Ambiguity Sets6 May 2025
29 more
- 2025A Dictionary of Closed-Form Kernel Mean Embeddings26 Apr 2025
- 2025Simulation-based Bayesian inference under model misspecification16 Mar 2025
- 2025A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimation11 Mar 2025
- 2025Robust Simulation-Based Inference under Missing Data via Neural Processes3 Mar 2025
- 2025SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era10 Feb 2025
- 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data23 Jan 2025
- 2024Cost-aware simulation-based inference10 Oct 2024
- 2024A Comprehensive Guide to Simulation-based Inference in Computational Biology29 Sep 2024
- 2024On the Robustness of Kernel Goodness-of-Fit Tests11 Aug 2024
- 2024Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigation5 Jun 2024
- 2024Robust Kernel Hypothesis Testing under Data Corruption30 May 2024
- 2024Addressing Misspecification in Simulation-based Inference through Data-driven Calibration14 May 2024
- 2024Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation12 Feb 2024
- 2023Pseudo-Likelihood Inference28 Nov 2023
- 2023Robust and Conjugate Gaussian Process Regression1 Nov 2023
- 2023Sensitivity-Aware Amortized Bayesian Inference17 Oct 2023
- 2023A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancy27 Aug 2023
- 2023Robust Bayesian Inference for Measurement Error Misspecification: The Berkson and Classical Cases2 Jun 2023
- 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecification25 May 2023
- 2023Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation24 May 2023
- 2023Adversarial robustness of amortized Bayesian inference24 May 2023
- 2023A Semi-Bayesian Nonparametric Estimator of the Maximum Mean Discrepancy Measure: Applications in Goodness-of-Fit Testing and Generative Adversarial Networks5 Mar 2023
- 2023Robust and Scalable Bayesian Online Changepoint Detection9 Feb 2023
- 2023Misspecification-robust Sequential Neural Likelihood for Simulation-based Inference31 Jan 2023
- 2023Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference27 Jan 2023
- 2022Targeted Separation and Convergence with Kernel Discrepancies26 Sep 2022
- 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inference5 Sep 2022
- 2022Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation29 Aug 2022
- 2022Generalised Bayesian Inference for Discrete Intractable Likelihood16 Jun 2022
- 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
- 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 44
- 2022Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimationcited by 27
- 2024Addressing Misspecification in Simulation-based Inference through Data-driven Calibrationcited by 26
- 2023Sensitivity-Aware Amortized Bayesian Inferencecited by 20
- 2023Adversarial robustness of amortized Bayesian inferencecited by 17
- 2023Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimationcited by 17
- 2023Robust and Scalable Bayesian Online Changepoint Detectioncited by 16
- 2022Targeted Separation and Convergence with Kernel Discrepanciescited by 15
- 2022Generalised Bayesian Inference for Discrete Intractable Likelihoodcited by 14
- 2023Robust and Conjugate Gaussian Process Regressioncited by 14
- 2023Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inferencecited by 13
12 most cited of 41 All 41 (JSON)
- 2026A Gradient Flow Perspective on Minimum MMD Estimation4 Jul 2026
- 2026Variational predictive resampling11 May 2026
- 2026Unsupervised Continual Learning for Amortized Bayesian Inference26 Feb 2026
- 2026Minimum Distance Summaries for Robust Neural Posterior Estimation9 Feb 2026
- 2025Robust Bayesian Optimisation with Unbounded Corruptions19 Nov 2025
- 2025Multi-Output Robust and Conjugate Gaussian Processes30 Oct 2025
- 2025TabMGP: Martingale Posterior with TabPFN29 Oct 2025
- 2025Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference2 Oct 2025
- 2025Misspecification-robust amortised simulation-based inference using variational methods6 Sep 2025
- 2025Causal Posterior Estimation27 May 2025
- 2025Uncertainty-Aware Surrogate-based Amortized Bayesian Inference for Computationally Expensive Models13 May 2025
- 2025Decision Making under Model Misspecification: DRO with Robust Bayesian Ambiguity Sets6 May 2025
12 newest of 41 All 41 (JSON)