Conditional variational autoencoder inference of neutron star equation of state from astrophysical observations

With Márcio Ferreira, we have developed a new machine-learning inference method to estimate the neutron star (NS) equation of state (EOS) from astrophysical observations, based on a conditional variational autoencoder (CVAE) architecture. The CVAE is trained on a large set of NS EOS models and their corresponding mass and radius ‘‘observations’’. Our results show robust reconstructing performance of the model, allowing to make instantaneous inference from any given observation set.

See arXiv:2503.14266 for details.