Dingo
Dingo (Deep Inference for Gravitational-wave Observations) is a Python program for analyzing gravitational wave data using neural posterior estimation. It dramatically speeds up inference of astrophysical source parameters from data measured at gravitational-wave observatories. Dingo aims to enable the routine use of the most advanced theoretical models in analysing data, to make rapid predictions for multi-messenger counterparts, and to do so in the context of sensitive detectors with high event rates.
The basic approach of Dingo is to train a neural network to represent the Bayesian posterior, conditioned on data. This enables amortized inference: when new data are observed, they can be plugged in and results obtained in a small amount of time. Tasks handled by Dingo include
training normalizing flows to estimate the posterior density;
performing inference on real or simulated data; and
verifying and correcting model results using importance sampling.
As training a network from scratch can be expensive, we intend to also distribute trained networks that can be used directly for inference. These can be used with dingo_pipe to automate analysis of gravitational wave events.
Getting started
Advanced guide
API
References
Dingo is based on a series of papers developing neural posterior estimation for gravitational waves, starting from proof of concept [1], to inclusion of all 15 parameters and analysis of real data [2], noise conditioning and full amortization [3], and group-equivariant NPE [4]. Dingo results are augmented with importance sampling in [5]. Finally, training with forecasted noise (needed for training prior to an observing run) is described in [6].
Stephen R. Green, Christine Simpson, and Jonathan Gair. Gravitational-wave parameter estimation with autoregressive neural network flows. Phys. Rev. D, 102:104057, 2020. arXiv:2002.07656, doi:10.1103/PhysRevD.102.104057.
Stephen R. Green and Jonathan Gair. Complete parameter inference for GW150914 using deep learning. Mach. Learn. Sci. Tech., 2(3):03LT01, 2021. arXiv:2008.03312, doi:10.1088/2632-2153/abfaed.
Maximilian Dax, Stephen R. Green, Jonathan Gair, Jakob H. Macke, Alessandra Buonanno, and Bernhard Schölkopf. Real-Time Gravitational Wave Science with Neural Posterior Estimation. Phys. Rev. Lett., 127(24):241103, 2021. arXiv:2106.12594, doi:10.1103/PhysRevLett.127.241103.
Maximilian Dax, Stephen R. Green, Jonathan Gair, Michael Deistler, Bernhard Schölkopf, and Jakob H. Macke. Group equivariant neural posterior estimation. International Conference on Learning Representations, 2022. arXiv:2111.13139.
Maximilian Dax, Stephen R. Green, Jonathan Gair, Michael Pürrer, Jonas Wildberger, Jakob H. Macke, Alessandra Buonanno, and Bernhard Schölkopf. Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference. 10 2022. arXiv:2210.05686.
Jonas Wildberger, Maximilian Dax, Stephen R. Green, Jonathan Gair, Michael Pürrer, Jakob H. Macke, Alessandra Buonanno, and Bernhard Schölkopf. Adapting to noise distribution shifts in flow-based gravitational-wave inference. 11 2022. arXiv:2211.08801.
If you use Dingo in your work, we ask that you please cite at least [3].
Contributors to the code are listed in AUTHORS.md. We thank Vivien Raymond and Rory Smith for acting as LIGO-Virgo-KAGRA (LVK) code reviewers. Dingo makes use of many LVK software tools, including Bilby, bilby_pipe, and LALSimulation, as well as third party tools such as PyTorch and nflows.
Contact
For questions or comments please contact Maximilian Dax or Stephen Green.