REVIEW 24 cited by
Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference
read the original abstract
We combine amortized neural posterior estimation with importance sampling for fast and accurate gravitational-wave inference. We first generate a rapid proposal for the Bayesian posterior using neural networks, and then attach importance weights based on the underlying likelihood and prior. This provides (1) a corrected posterior free from network inaccuracies, (2) a performance diagnostic (the sample efficiency) for assessing the proposal and identifying failure cases, and (3) an unbiased estimate of the Bayesian evidence. By establishing this independent verification and correction mechanism we address some of the most frequent criticisms against deep learning for scientific inference. We carry out a large study analyzing 42 binary black hole mergers observed by LIGO and Virgo with the SEOBNRv4PHM and IMRPhenomXPHM waveform models. This shows a median sample efficiency of $\approx 10\%$ (two orders-of-magnitude better than standard samplers) as well as a ten-fold reduction in the statistical uncertainty in the log evidence. Given these advantages, we expect a significant impact on gravitational-wave inference, and for this approach to serve as a paradigm for harnessing deep learning methods in scientific applications.
Forward citations
Cited by 24 Pith papers
-
Joint inference of line-of-sight acceleration and orbital eccentricity in neutron-star--black-hole binaries
All five NSBH events are consistent with zero line-of-sight acceleration; the joint posterior for GW200105_162426 disfavors both zero LOSA and zero eccentricity at 90% credibility.
-
Contrastive self-supervised convolutional autoencoder for core-collapse supernova gravitational-wave detection
A contrastive self-supervised convolutional autoencoder detects core-collapse supernova gravitational waves with performance comparable to supervised CNNs, better generalization to unseen waveforms, and ~120 kpc sensi...
-
Ab Initio Real-Time Gravitational-Wave Parameter Estimation
Slice-within-Gibbs nested sampling on modern GPUs delivers well-calibrated BNS parameter estimation in ~12 minutes uncompressed and ~89 seconds with heterodyning, from cold priors.
-
Fast, accurate, and differentiable: a neural-network surrogate for NRSur7dq4 precessing binary black hole waveforms
A piecewise MLP surrogate emulates NRSur7dq4 over its full domain at NR-faithful accuracy with ~1 ms GPU latency and a fully differentiable JAX likelihood pipeline.
-
Identifying lensed gravitational waves with physics-informed posterior learning
Fusing a simulation-trained common-source mass posterior with waveform features raises lensed-event detection efficiency from 20.8% to 35.2% at 1% false-positive rate and lowers the SNR for 50% efficiency from 45.3 to 33.5.
-
Flow-Based Surrogates for High-Dimensional Likelihoods in Experimental Neutrino Physics
A hybrid coupling-plus-autoregressive normalizing flow trained on a 110-parameter T2K-like near-detector likelihood reaches 98% relative ESS versus 5% for the post-fit Gaussian and matches MCMC flux predictions.
-
Flow-Based Surrogates for High-Dimensional Likelihoods in Experimental Neutrino Physics
A hybrid coupling-plus-autoregressive normalizing flow reproduces a 110-parameter non-Gaussian near-detector likelihood at 98% relative ESS versus ~5% for the post-fit Gaussian, matching MCMC while remaining evaluable...
-
Fortifying gravitational-wave population inference with normalizing flows
Representing each gravitational-wave event's posterior with a normalizing flow lets analysts generate enough cheap posterior samples to keep the Monte-Carlo variance of population inference below threshold for catalog...
-
Eccentric and unbound compact binaries in the LIGO-Virgo-KAGRA catalog: parameter estimation and waveform systematics with SEOBNRv6EHM
SEOBNRv6EHM reduces parameter biases for eccentric binaries versus prior models and shows mild support for eccentricity in five catalog events plus comparable unbound fits for three high-mass events.
-
Robust parameter inference for Taiji via time-frequency contrastive learning and normalizing flows
A glitch-robust amortized inference framework combining normalizing flows, time-frequency multimodal fusion, and contrastive learning outperforms MCMC for Taiji massive black hole binary parameter estimation under noi...
-
Combining simulation-based inference and universal relations for precise and accurate neutron star science
A machine-learning simulator trained on 1,491 simulated equations of state discovers a neutron-star radius relation R(M,f,p1), predicting radii to tens of meters with calibrated error bars.
-
Model-agnostic search of gravitational wave echoes in LVK data
A multi-detector phase-marginalized echo search finds no statistically significant long-lived quasinormal-mode echoes in GW150914, GW231226, and GW250114, and sets 90% upper limits on their network SNR and amplitude.
-
Flexible Gravitational-Wave Parameter Estimation with Transformers
Dingo-T1 is one transformer model that adapts at inference to arbitrary detector subsets and frequency cuts for gravitational-wave parameter estimation.
-
Accelerated Sequential Posterior Inference via Reuse for Gravitational-Wave Analyses
ASPIRE reuses old posterior samples via normalizing flows and sequential Monte Carlo to produce unbiased posteriors and evidences under new models, cutting likelihood evaluations 4-10x.
-
A Robust and Efficient F-statistic-based Framework for Consistent Bayesian Inference of Compact Binary Coalescences
F-statistic framework analytically maximizes over distance and polarization to enable faster Bayesian inference of compact binary coalescences with a new evidence formulation that matches full frequency-domain results...
-
Parameter inference of millilensed gravitational waves using neural spline flows
Neural spline flows perform fast posterior inference on 11-dimensional millilensed GW parameters with accuracy comparable to dynesty for most quantities and a 3-day to 0.8-second speedup.
-
Evidence for eccentricity in the population of binary black holes observed by LIGO-Virgo-KAGRA
Bayesian inference on LVK O1-O3 events with eccentric aligned-spin waveforms yields log10 Bayes factors of 1.77-4.75 favoring eccentricity for GW200129, GW190701 and GW200208_22, and >99.5% probability that at least o...
-
Artifact-Conditioned Interval Diagnostics for Flow-Matching Neural Posterior Estimation in a Controlled Gravitational-Wave Benchmark
In a controlled binary-black-hole benchmark, soft learned artifact-aware interval rescaling (LAIR) reduces marginal calibration error for frequency masks from 0.1195 to 0.0672 but is not uniformly better than raw inte...
-
Speed and accuracy for long signals: Frequency-domain effective-one-body waveforms for compact binary coalescences
Hybrid SPA-plus-FFT frequency-domain version of SEOBNRv5THM for quasi-circular spin-aligned BNS systems matches time-domain baseline accuracy while cutting computational cost for long signals.
-
Spectroscopy of analogue black holes using simulation-based inference
Simulation-based inference reliably extracts physical parameters from noisy spectra of analogue black holes.
-
Discovering gravitational waveform distortions from lensing: A deep dive into GW231123
GW231123's apparent gravitational-lensing signal has a false-alarm probability around 4σ, so the event cannot be claimed as lensed under the two-image wave-optics model.
-
Accelerated inference of microlensed gravitational waves with machine learning
A neural posterior estimator trained on wave-optics-microlensed gravitational-wave signals recovers source and lens parameters and Bayes factors consistent with Bilby, about 10 times faster.
-
Assessment of normalizing flows for parameter estimation on time-frequency representations of gravitational-wave data
GP15 maps BBH spectrograms to parameter posteriors via residual networks and normalizing flows, producing results consistent with LVK analyses on GWTC-2.1 and GWTC-3 events while running in seconds.
-
An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning
A structured introduction to ML-based simulation-based inference, contrasting Bayesian and frequentist frameworks and covering parameter inference, unfolding, and validation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.