Flexible Gravitational-Wave Parameter Estimation with Transformers
Open Access
- 23 June 2026
- journal article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 136 (25) , 251401
Abstract
Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of observations represent a growing challenge. Deep learning provides a powerful alternative to traditional inference, but existing neural models typically lack the flexibility to handle variations in data analysis settings. Such variations accommodate imperfect observations or are required for specialized tests, and could include changes in detector configurations, overall frequency ranges, or localized cuts. We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time. Applied to parameter estimation, we demonstrate that a flexible model—called -1—can (i) analyze 48 binary black holes from the third LIGO-Virgo-KAGRA Observing Run under a wide range of analysis configurations, (ii) enable systematic studies of how detector and frequency configurations impact inferred posteriors, and (iii) perform inspiral-merger-ringdown consistency tests probing general relativity. -1 also improves median sample efficiency on real events from a baseline of 1.4% to 4.2%. Our approach thus demonstrates flexible and scalable inference with a principled framework for handling missing or incomplete data—key capabilities for current and next-generation observatories.Keywords
All Related Versions
Funding Information
- UK Research and Innovation (MR/Y018060/1)
- European Research Council (GWSky–101167314)
- National Science Foundation
- Science and Technology Facilities Council
- Max-Planck-Gesellschaft
- Australian Research Council
- Centre National de la Recherche Scientifique
- Istituto Nazionale di Fisica Nucleare Sezione di Padova
- Ministry of Education, Culture, Sports, Science and Technology
- Japan Society for the Promotion of Science
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea
- Academia Sinica
- National Science and Technology Council
- International Max Planck Research School for Intelligent Systems
- State of Niedersachsen/Germany
- European Gravitational Observatory
- Dutch Nikhef
This publication has 56 references indexed in Scilit:
- Real-time inference for binary neutron star mergers using machine learningNature, 2025
- Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomyNature Physics, 2021
- Array programming with NumPyNature, 2020
- SWIGLAL: Python and Octave interfaces to the LALSuite gravitational-wave data analysis librariesSoftwareX, 2020
- The frontier of simulation-based inferenceProceedings of the National Academy of Sciences, 2020
- Testing general relativity using gravitational wave signals from the inspiral, merger and ringdown of binary black holesClassical and Quantum Gravity, 2017
- Accelerating gravitational wave parameter estimation with multi-band template interpolationClassical and Quantum Gravity, 2017
- Bayeswave: Bayesian inference for gravitational wave bursts and instrument glitchesClassical and Quantum Gravity, 2015
- Advanced LIGOClassical and Quantum Gravity, 2015
- Advanced Virgo: a second-generation interferometric gravitational wave detectorClassical and Quantum Gravity, 2014