mlsanityData to 7 Oct 2026

Cost-aware simulation-based inference

arXiv 2410.07930 ↗First posted 10 Oct 2024stat.ML cs.LG stat.COcited by 6

Not on the map. Why?

Abstract (arXiv)

Simulation-based inference (SBI) is the preferred framework for estimating parameters of intractable models in science and engineering. A significant challenge in this context is the large computational cost of simulating data from complex models, and the fact that this cost often depends on parameter values. We therefore propose textitcost-aware SBI methods which can significantly reduce the cost of existing sampling-based SBI methods, such as neural SBI and approximate Bayesian computation. This is achieved through a combination of rejection and self-normalised importance sampling, which significantly reduces the number of expensive simulations needed. Our approach is studied extensively on models from epidemiology to telecommunications engineering, where we obtain significant reductions in the overall cost of inference.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 81 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

27 of 81 references.

References · 27

  1. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  2. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  3. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
  4. 2019The frontier of simulation-based inferencecited by 490
  5. 2016Revisiting Classifier Two-Sample Testscited by 258
  6. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  7. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  8. 2021Benchmarking Simulation-Based Inferencecited by 160
  9. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  10. 2020On Contrastive Learning for Likelihood-free Inferencecited by 96
  11. 2015Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Modelscited by 61
  12. 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
15 more
  1. 2019Statistical Inference for Generative Models with Maximum Mean Discrepancycited by 43
  2. 2020Cost-aware Bayesian Optimizationcited by 41
  3. 2022Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrapcited by 41
  4. 2023Bayesian Synthetic Likelihoodcited by 29
  5. 2022Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inferencecited by 28
  6. 2014GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computationcited by 17
  7. 2017Efficient acquisition rules for model-based approximate Bayesian computationcited by 16
  8. 2021Composite Goodness-of-fit Tests with Kernelscited by 16
  9. 2023Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inferencecited by 13
  10. 2023AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designscited by 13
  11. 2021Discrepancy-based Inference for Intractable Generative Models using Quasi-Monte Carlocited by 12
  12. 2021Generalized Bayesian Likelihood-Free Inferencecited by 11
  13. 2022Approximate Bayesian Computation with Domain Expert in the Loopcited by 9
  14. 2014Accelerating ABC methods using Gaussian processescited by 7
  15. 2019Distilling Importance Sampling for Likelihood Free Inferencecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.

  1. 2024Compositional simulation-based inference for time seriescited by 8
  2. 2025Multilevel neural simulation-based inferencecited by 5
  3. 2026Constrained Bayesian Experimental Design via Online Planningcited by 2
  4. 2026Simulation-Based Inference via Regression Projection and Batched Discrepanciescited by 0
  5. 2026Conservative neural posterior estimation via distributionally robust trainingcited by 0
  6. 2026Exploiting Gradients in Bayesian Inference of Expensive Simulatorscited by 0