BilbyFlow: user-friendly neural posterior estimation for gravitational-wave astronomy
Abstract
Bayesian inference plays a central role in the new field of gravitational-wave astronomy. However, traditional Bayesian inference with stochastic samplers is computationally expensive, taking hours to days per event. Transformative changes are therefore required to enable the science of next-generation observatories whose event rates and signal-to-noise ratios will increase significantly over the current generation. Recent work has shown that neural posterior estimation (NPE) is a promising path forward. A neural net is trained to approximate the posterior distribution of gravitational-wave parameters, allowing generation of posterior samples in a fraction of the time required by stochastic samplers. In this work, we introduce BilbyFlow, which harnesses the power of NPE in the popular Bilby code suite. We use BilbyFlow to analyze a subset of 38 high-mass events from the third LIGO-Virgo-KAGRA Gravitational-Wave Transient Catalog (GWTC-3). For 29 events (76\%), we obtained an importance-sampling efficiency >1%, allowing us to produce reliable posterior distributions within 3 min - 1.5 hours. For the other events, with importance-sampling efficiency ≪1%, the run time can be as long as 35 hours. We achieve a median importance-sampling efficiency of 7%, which is roughly comparable to the DINGO package. We aim to significantly improve this efficiency with further development to make the runtime more reliably O(min). BilbyFlow is open source and pip-installable.
Related
- Searching for gravitational wave echo with group equivariant neural posterior estimation
- The Promise of Gravitational-Wave Astronomy
- Latin hypercube sampling to reduce the variance in Monte Carlo integration: a practical guide and an application to gravitational-wave astronomy
- Population-level correlations in Bayesian statistics: an illustrative model for gravitational-wave astronomy
- gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
BibTeX
@misc{pinchbeck2026bilbyflow,
title = {{$\textttBilbyFlow$: user-friendly neural posterior estimation for gravitational-wave astronomy}},
author = {Liam Pinchbeck and Eric Thrane and Csaba Balazs and Paul Lasky},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00766},
eprint = {2609.00766},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00766},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - BilbyFlow: user-friendly neural posterior estimation for gravitational-wave astronomy
AU - Liam Pinchbeck
AU - Eric Thrane
AU - Csaba Balazs
AU - Paul Lasky
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00766
UR - https://arxiv.org/abs/2609.00766
AB - Bayesian inference plays a central role in the new field of gravitational-wave astronomy. However, traditional Bayesian inference with stochastic samplers is computationally expensive, taking hours to days per event. Transformative changes are therefore required to enable the science of next-generation observatories whose event rates and signal-to-noise ratios will increase significantly over the current generation. Recent work has shown that neural posterior estimation (NPE) is a promising path forward. A neural net is trained to approximate the posterior distribution of gravitational-wave parameters, allowing generation of posterior samples in a fraction of the time required by stochastic samplers. In this work, we introduce BilbyFlow, which harnesses the power of NPE in the popular Bilby code suite. We use BilbyFlow to analyze a subset of 38 high-mass events from the third LIGO-Virgo-KAGRA Gravitational-Wave Transient Catalog (GWTC-3). For 29 events (76\%), we obtained an importance-sampling efficiency >1%, allowing us to produce reliable posterior distributions within 3 min - 1.5 hours. For the other events, with importance-sampling efficiency ≪1%, the run time can be as long as 35 hours. We achieve a median importance-sampling efficiency of 7%, which is roughly comparable to the DINGO package. We aim to significantly improve this efficiency with further development to make the runtime more reliably O(min). BilbyFlow is open source and pip-installable.
ER -