Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware
This enables rapid alerts for gravitational-wave astronomy, though it is incremental as it builds on existing likelihood-free inference and hardware acceleration methods.
The authors tackled the problem of real-time parameter estimation for gravitational-wave signals from compact binary coalescences, achieving a net latency of ~6 seconds for inferring parameters from data acquisition using their AMPLFI algorithm combined with Aframe.
We report a gravitational-wave parameter estimation algorithm, AMPLFI, based on likelihood-free inference using normalizing flows. The focus of AMPLFI is to perform real-time parameter estimation for candidates detected by machine-learning based compact binary coalescence search, Aframe. We present details of our algorithm and optimizations done related to data-loading and pre-processing on accelerated hardware. We train our model using binary black-hole (BBH) simulations on real LIGO-Virgo detector noise. Our model has $\sim 6$ million trainable parameters with training times $\lesssim 24$ hours. Based on online deployment on a mock data stream of LIGO-Virgo data, Aframe + AMPLFI is able to pick up BBH candidates and infer parameters for real-time alerts from data acquisition with a net latency of $\sim 6$s.