Deep Generative Models of Gravitational Waveforms via Conditional Autoencoder. (arXiv:2101.06685v3 [astro-ph.IM] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Liao_C/0/1/0/all/0/1">Chung-Hao Liao</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Lin_F/0/1/0/all/0/1">Feng-Li Lin</a>
We construct few deep generative models of gravitational waveforms based on
the semi-supervising scheme of conditional autoencoders and their variational
extensions. Once the training is done, we find that our best waveform model can
generate the inspiral-merger waveforms of binary black hole coalescence with
more than $97%$ average overlap matched filtering accuracy for the mass ratio
between $1$ and $10$. Besides, the generation time of a single waveform takes
about one millisecond, which is about $10$ to $100$ times faster than the EOBNR
algorithm running on the same computing facility. Moreover, these models can
also help to explore the space of waveforms. That is, with mainly the
low-mass-ratio training set, the resultant trained model is capable of
generating large amount of accurate high-mass-ratio waveforms. This result
implies that our generative model can speed up the waveform generation for the
low latency search of gravitational wave events. With the improvement of the
accuracy in future work, the generative waveform model may also help to speed
up the parameter estimation and can assist the numerical relativity in
generating the waveforms of higher mass ratio by progressively self-training.
We construct few deep generative models of gravitational waveforms based on
the semi-supervising scheme of conditional autoencoders and their variational
extensions. Once the training is done, we find that our best waveform model can
generate the inspiral-merger waveforms of binary black hole coalescence with
more than $97%$ average overlap matched filtering accuracy for the mass ratio
between $1$ and $10$. Besides, the generation time of a single waveform takes
about one millisecond, which is about $10$ to $100$ times faster than the EOBNR
algorithm running on the same computing facility. Moreover, these models can
also help to explore the space of waveforms. That is, with mainly the
low-mass-ratio training set, the resultant trained model is capable of
generating large amount of accurate high-mass-ratio waveforms. This result
implies that our generative model can speed up the waveform generation for the
low latency search of gravitational wave events. With the improvement of the
accuracy in future work, the generative waveform model may also help to speed
up the parameter estimation and can assist the numerical relativity in
generating the waveforms of higher mass ratio by progressively self-training.
http://arxiv.org/icons/sfx.gif
