Neural network surrogate approximates precessing compact binary gravitational waveforms up to 1000x faster than the base EOB model with validated accuracy.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
gr-qc 2roles
background 1polarities
background 1representative citing papers
GP15, a ResNet plus normalizing-flow model trained on stacked spectrograms, recovers most binary black hole parameters in agreement with LVK posteriors on 33 three-detector events, with generation of 10,000 posterior samples in about one second.
citing papers explorer
-
Fast neural network surrogate for multimodal effective-one-body gravitational waveforms from generically precessing compact binaries
Neural network surrogate approximates precessing compact binary gravitational waveforms up to 1000x faster than the base EOB model with validated accuracy.
-
Assessment of normalizing flows for parameter estimation on time-frequency representations of gravitational-wave data
GP15, a ResNet plus normalizing-flow model trained on stacked spectrograms, recovers most binary black hole parameters in agreement with LVK posteriors on 33 three-detector events, with generation of 10,000 posterior samples in about one second.