Reduced-order modeling with artificial neurons for gravitational-wave inference
This work addresses computational efficiency in gravitational-wave data analysis for astrophysicists, but it is incremental as it builds on existing reduced-order modeling techniques.
The authors tackled the problem of gravitational-wave inference by representing waveforms as weighted sums over reduced bases and training neural networks to map source parameters to basis coefficients, achieving fast and accurate coefficient interpolation for a four-dimensional binary-inspiral waveform family.
Gravitational-wave data analysis is rapidly absorbing techniques from deep learning, with a focus on convolutional networks and related methods that treat noisy time series as images. We pursue an alternative approach, in which waveforms are first represented as weighted sums over reduced bases (reduced-order modeling); we then train artificial neural networks to map gravitational-wave source parameters into basis coefficients. Statistical inference proceeds directly in coefficient space, where it is theoretically straightforward and computationally efficient. The neural networks also provide analytic waveform derivatives, which are useful for gradient-based sampling schemes. We demonstrate fast and accurate coefficient interpolation for the case of a four-dimensional binary-inspiral waveform family, and discuss promising applications of our framework in parameter estimation.