Rapid likelihood free inference of compact binary coalescences using accelerated hardware
Deep Chatterjee, Ethan Marx, Will Benoit, Ravi Kumar, Malina Desai, Ekaterina Govorkova, Alec Gunny, Eric Moreno, Rafia Omer, Ryan Raikman, M. Saleem, Shrey Aggarwal, M. W. Coughlin, Philip Harris, E. Katsavounidis
Abstract
Abstract 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 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mrow> <mml:mo>∼</mml:mo> </mml:mrow> <mml:mn>6</mml:mn> </mml:mrow> </mml:math> million trainable parameters with training times <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mrow> <mml:mo>≲</mml:mo> </mml:mrow> <mml:mn>24</mml:mn> </mml:mrow> </mml:math> h. 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 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mrow> <mml:mo>∼</mml:mo> </mml:mrow> <mml:mn>6</mml:mn> </mml:mrow> </mml:math> s.