Unsupervised Neural Operators for Rotating Relativistic Stars: High-Fidelity Equation of State Inference and Pulsar Spin Evolution at Scale
Abstract
Observed populations of rotating neutron stars~(NSs) with millisecond-order periods are powerful probes of fundamental physics. Mass-radius measurements inform poorly constrained properties of degenerate nuclear matter, whereas high-fidelity population synthesis connects unknowns in NS formation and binary evolution to large radio-timing surveys. However, repeated structure calculations are prohibitive due to the computational cost of solving the highly coupled partial differential equations of axisymmetric general relativistic hydrostatic equilibrium that govern rotating NS interiors. Non-rotating calculations or approximate rotational corrections can bias equation of state inference and limit the fidelity of population synthesis in tracing the evolutionary history of progenitors and propagating equation of state uncertainties. In this \textit{Letter}, we develop physics-informed neural operators that can solve the axisymmetric problem with high accuracy and negligible computational cost. \textit{Our solvers are trained in a fully unsupervised setting, with the training objective informed solely by the partial differential equations, and achieve a 103× speed-up with negligible accuracy loss}. These solvers enable scalable EoS inference that self-consistently accounts for rotation and repeated stellar-structure calculations during binary evolution, making spin predictions that account for rotational structure and EoS uncertainties computationally accessible to population synthesis.
Related
- General Relativistic Simulations of the Nonlinear Evolution of r-modes in Rapidly Rotating Neutron Stars
- Heat propagation in rotating relativistic bodies
- Quasi-normal Modes and Instabilities of Rotating Relativistic Stars
- Rotating models of very massive close binary stars at solar metallicity: Evolution and remnant masses
- FUGUE: A New GPU-accelerated General Relativistic Magnetohydrodynamics Code with Weak-Field Multipole Self-Gravity and Quasi-Stationary Kerr Black Hole Evolution
BibTeX
@misc{ray2026unsupervised,
title = {{Unsupervised Neural Operators for Rotating Relativistic Stars: High-Fidelity Equation of State Inference and Pulsar Spin Evolution at Scale}},
author = {Anarya Ray},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.05790},
eprint = {2611.05790},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.05790},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Unsupervised Neural Operators for Rotating Relativistic Stars: High-Fidelity Equation of State Inference and Pulsar Spin Evolution at Scale
AU - Anarya Ray
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.05790
UR - https://arxiv.org/abs/2611.05790
AB - Observed populations of rotating neutron stars~(NSs) with millisecond-order periods are powerful probes of fundamental physics. Mass-radius measurements inform poorly constrained properties of degenerate nuclear matter, whereas high-fidelity population synthesis connects unknowns in NS formation and binary evolution to large radio-timing surveys. However, repeated structure calculations are prohibitive due to the computational cost of solving the highly coupled partial differential equations of axisymmetric general relativistic hydrostatic equilibrium that govern rotating NS interiors. Non-rotating calculations or approximate rotational corrections can bias equation of state inference and limit the fidelity of population synthesis in tracing the evolutionary history of progenitors and propagating equation of state uncertainties. In this \textit{Letter}, we develop physics-informed neural operators that can solve the axisymmetric problem with high accuracy and negligible computational cost. \textit{Our solvers are trained in a fully unsupervised setting, with the training objective informed solely by the partial differential equations, and achieve a 10^3× speed-up with negligible accuracy loss}. These solvers enable scalable EoS inference that self-consistently accounts for rotation and repeated stellar-structure calculations during binary evolution, making spin predictions that account for rotational structure and EoS uncertainties computationally accessible to population synthesis.
ER -