Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
Published in Nature Physics, 2021
Using conditional variational autoencoders we are able to reproduce the Bayesian posterior for several simulated GW events. We compare our results to standard Bayesian inference techniques from the Bilby Bayesian inference library and are able to achieve ~6 orders of magnitude speed-up in performance.
Recommended citation: Gabbard, H., Messenger, C., Heng, I.S. et al. Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy. Nat. Phys. 18, 112–117 (2022). https://doi.org/10.1038/s41567-021-01425-7 https://www.nature.com/articles/s41567-021-01425-7