REVIEW 17 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
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 17 Pith papers
-
Hierarchical Subtraction with Neural Density Estimators as a General Solution to Overlapping Gravitational Wave Signals
The paper introduces an iterative, ensemble-based hierarchical subtraction scheme powered by neural density estimators that recovers overlapping gravitational wave signals accurately and fast.
-
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.
-
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...
-
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.
-
The fault in our sirens: Hierarchical diagnosis of waveform systematics in Hubble-Lema\^itre constant measurements
A 5% subpopulation of high-mass, spin-precessing black hole binaries, poorly modeled by current waveforms, makes future dark-siren Hubble constant measurements unreliable, and a hierarchical variance diagnostic can de...
-
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.
-
Robustness of Sensitivity Evaluations for Gravitational Wave Detection Algorithms
AresGW model 1's injection detection count at a false-alarm rate of 1/month varies with noise dataset by up to 39% coefficient of variation, while sensitive distance varies by only a few percent.
-
Revisiting GW150914 with a non-planar, eccentric waveform model
Using a waveform model that includes both eccentricity and spin precession, the authors confirm GW150914 was a quasi-circular, slowly spinning black hole merger, with eccentricity below 0.08 at 15 Hz.
-
A fast deep-learning approach to probing primordial black hole populations in gravitational wave events
A neural network maps single-event gravitational-wave posterior samples to joint PBH population posteriors in about one second on a GPU, with calibration matching MCMC on simulated catalogs.
-
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). Continue with ORCID to comment.