Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy

With the improving sensitivity of the global network of gravitational-wave detectors, we expect to observe hundreds of transient gravitational-wave events per year. The current methods used to estimate their source parameters employ optimally sensitive but computationally costly Bayesian inference approaches, where typical analyses have taken between 6 h and 6 d. For binary neutron star and neutron star-black hole systems prompt counterpart electromagnetic signatures are expected on timescales between 1 s and 1 min. However, the current fastest method for alerting electromagnetic follow-up observers can provide estimates in of the order of 1 min on a limited range of key source parameters. Here, we show that a conditional variational autoencoder pretrained on binary black hole signals can return Bayesian posterior probability estimates. The training procedure need only be performed once for a given prior parameter space and the resulting trained machine can then generate samples describing the posterior distribution around six orders of magnitude faster than existing techniques. A method for estimating the source properties of gravitational-wave events shows a speed-up of six orders of magnitude over established approaches. This is a promising tool for follow-up observations of electromagnetic counterparts.

Automated summary

The study shows that a conditional variational autoencoder pretrained on binary black hole signals can return Bayesian posterior probability estimates. The training process only needs to be done once for a specific prior parameter space, and the resulting trained machine can generate samples describing the posterior distribution six orders of magnitude faster than existing techniques. This method offers a significant speed-up in estimating the source properties of gravitational-wave events and is a promising tool for follow-up observations of electromagnetic counterparts.