mlsanityData to 13 Oct 2026

Real-time gravitational-wave science with neural posterior estimation

arXiv 2106.12594 ↗First posted 23 Jun 2021gr-qc astro-ph.IM cs.LGcited by 76

Not on the map. Why?

Abstract (arXiv)

We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event. Our networks are trained using simulated data, including an estimate of the detector-noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters, and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm -- called "DINGO" -- sets a new standard in fast-and-accurate inference of physical parameters of detected gravitational-wave events, which should enable real-time data analysis without sacrificing accuracy.

Key facts. Cited by 76 papers in the map (data through 13 Oct 2026). Builds on 16 of its 64 references that are in the map. First posted on arXiv 23 Jun 2021.

Builds on

16 of 64 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  4. 2015Variational Inference with Normalizing Flowscited by 2,163
  5. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  6. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 638
  7. 2019Neural Spline Flowscited by 590
  8. 2019The frontier of simulation-based inferencecited by 492
  9. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  10. 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
  11. 2019Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomycited by 36
  12. 2020Complete parameter inference for GW150914 using deep learningcited by 25
4 more
  1. 2020Gravitational-wave parameter estimation with autoregressive neural network flowscited by 19
  2. 2019Learning Bayesian posteriors with neural networks for gravitational-wave inferencecited by 18
  3. 2020Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortizationcited by 17
  4. 2019Statistically-informed deep learning for gravitational wave parameter estimationcited by 14

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 7; 2022: 9; 2023: 20; 2024: 11; 2025: 14; 2026: 15.

76 papers.

Sort:

By area:

  1. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 100
  2. 2024All-in-one simulation-based inferencecited by 71
  3. 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 45
  4. 2022From Statistical to Causal Learningcited by 40
  5. 2022Truncated proposals for scalable and hassle-free simulation-based inferencecited by 40
  6. 2025Simulation-Based Inference: A Practical Guidecited by 31
  7. 2021Truncated Marginal Neural Ratio Estimationcited by 30
  8. 2022Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inferencecited by 28
  9. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  10. 2024Real-time gravitational-wave inference for binary neutron stars using machine learningcited by 21
  11. 2023Sensitivity-Aware Amortized Bayesian Inferencecited by 20
  12. 2021Learn-Morph-Infer: a new way of solving the inverse problem for brain tumor modelingcited by 19
38 more
  1. 2023TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Seriescited by 17
  2. 2023Adversarial robustness of amortized Bayesian inferencecited by 17
  3. 2023L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inferencecited by 17
  4. 2021Group equivariant neural posterior estimationcited by 16
  5. 2023Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inferencecited by 14
  6. 2025SciTS: Scientific Time Series Understanding and Generation with LLMscited by 14
  7. 2021Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimationcited by 13
  8. 2023Simulation-based Inference for Cardiovascular Modelscited by 11
  9. 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Datacited by 11
  10. 2023Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?cited by 10
  11. 2023Simulation-based Inference for High-dimensional Data using Surjective Sequential Neural Likelihood Estimationcited by 8
  12. 2024Compositional simulation-based inference for time seriescited by 8
  13. 2022Machine Learning and Cosmologycited by 6
  14. 2024Preconditioned Neural Posterior Estimation for Likelihood-free Inferencecited by 6
  15. 2021Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergerscited by 5
  16. 2022Inference-optimized AI and high performance computing for gravitational wave detection at scalecited by 5
  17. 2022Uncertain Evidence in Probabilistic Models and Stochastic Simulatorscited by 5
  18. 2022Adapting to noise distribution shifts in flow-based gravitational-wave inferencecited by 5
  19. 2023AI for Science: An Emerging Agendacited by 5
  20. 2025Robust Simulation-Based Inference under Missing Data via Neural Processescited by 5
  21. 2021Swift sky localization of gravitational waves using deep learning seeded importance samplingcited by 4
  22. 2024Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimationcited by 4
  23. 2021AI and extreme scale computing to learn and infer the physics of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergerscited by 3
  24. 2023Simulation-based Inference with the Generalized Kullback-Leibler Divergencecited by 3
  25. 2023Simulation-based stackingcited by 3
  26. 2024Nonlinear denoising score matching for enhanced learning of structured distributionscited by 3
  27. 2023Discriminative calibration: Check Bayesian computation from simulations and flexible classifiercited by 2
  28. 2023nbi: the Astronomer's Package for Neural Posterior Estimationcited by 2
  29. 2024Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardwarecited by 2
  30. 2024Flow Matching for Posterior Inference with Simulator Feedbackcited by 2
  31. 2024Full-waveform earthquake source inversion using simulation-based inferencecited by 2
  32. 2025Simulation-based inference for Precision Neutrino Physics through Neural Monte Carlo tuningcited by 2
  33. 2026Scalable Simulation-Based Model Inference with Test-Time Complexity Controlcited by 2
  34. 2023Hyperparameter optimization of hp-greedy reduced basis for gravitational wave surrogatescited by 1
  35. 2023Optimizing Likelihood-free Inference using Self-supervised Neural Symmetry Embeddingscited by 1
  36. 2024Accelerated Bayesian parameter estimation and model selection for gravitational waves with normalizing flowscited by 1
  37. 2024A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveformscited by 1
  38. 2025Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformerscited by 1

50 most cited of 76 All 76 (JSON)