# Approximating neutron-star radii using gravitational-wave only measurements with symbolic regression

arXiv: https://arxiv.org/abs/2504.19962 · HTML: https://mlsanity.com/paper/2504.19962/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 59 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Builds on (most cited first, 4 of 4)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws](https://mlsanity.com/paper/2303.03192/) (2023)
- [Automated discovery of interpretable gravitational-wave population models](https://mlsanity.com/paper/2207.12409/) (2022)

## Abstract (arXiv)

Gravitational waves emitted by binary neutron-star inspirals carry information on components' masses and tidal deformabilities, but not directly radii, which are measured by electromagnetic observations of neutron stars. To improve the multi-messenger astronomy studies of neutron stars, an expression for neutron-star radii as a function of gravitational-wave only data would be advantageous, as it would allow to compare information from two different channels. In order to do so, a symbolic regression method, pySR, is trained on TOV solutions to piecewise polytropic EOS input to discover an approximate symbolic expression for the neutron-star radius as a function of gravitational-wave measurements only. The approximation is tested on piecewise polytropic EOS NS data, as well as on NS sequences based on selected realistic (non-polytropic) dense-matter theory EOSs, achieving consistent agreement between the ground truth values and the symbolic approximation for a broad range of NS parameters covering current astrophysical observations, with average radii differences of few hundred meters. Additionally, the approximation is applied to the GW170817 gravitational-wave mass and tidal deformability posteriors, and compared to reported inferred radius distributions.