Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
share
Gravitational wave (GW) detection is now commonplace and as the sensitivity of the global network of GW detectors improves, we will observe of order O(100)s of transient GW events per year. For each of these events the current methods used to estimate their source parameters employ optimally sensitive but computationally costly Bayesian inference approaches. For binary black hole (BBH) signals, existing complete GW analyses can take O(10^5 - 10^6) seconds to complete and for binary neutron star signals this increases by at least an order of magnitude. It is for this latter class of signal (and neutron star black hole systems) that counterpart electromagnetic (EM) signatures are expected, containing prompt emission on timescales of 1 second -- 1 minute. The current fastest method for alerting EM follow-up observers, can provide estimates in O(1) minute, on a limited range of key source parameters. Here we show that a conditional variational autoencoder pre-trained on BBH signals and without being given the precomputed posteriors can return Bayesian posterior probability estimates on source parameters. The training procedure need only be performed once for a given prior parameter space (or signal class) and the resulting trained machine can then generate samples describing the posterior distribution ∼ 7 orders of magnitude faster than existing techniques.
READ FULL TEXT
