Lightning-Fast Gravitational-Wave Parameter Inference Through Neural Amortization
AstroML
Andrew
Williamson
Date Submitted
2021-04-28 00:00:00
University of Portsmouth
Arnaud Delaunoy (University of Liège), Antoine Wehenkel (University of Liège), Tanja Hinderer (University of Utrecht), Samaya Nissanke (University of Amsterdam), Christoph Weniger (University of Amsterdam), Andrew Williamson (University of Portsmouth), Gilles Louppe (University of Liège)
Gravitational waves from compact binaries measured by the LIGO and Virgo detectors are routinely analyzed using Markov Chain Monte Carlo sampling algorithms. Because the evaluation of the likelihood function requires evaluating millions of waveform models that link between signal shapes and the source parameters, running Markov chains until convergence is typically expensive and requires days of computation. In this work, we provide a proof of concept that demonstrates how the latest advances in neural simulation-based inference can speed up the inference time by up to three orders of magnitude -- from days to minutes -- without impairing the performance. Our approach is based on a convolutional neural network modeling the likelihood-to-evidence ratio and entirely amortizes the computation of the posterior. We find that our model correctly estimates credible intervals for the parameters of simulated gravitational waves.
All attendees are expected to show respect and courtesy to other attendees and staff, and to adhere to the NAM Code of Conduct.