Reproduce “Black Hole Love Numbers with Physics-Informed Neural Networks” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Maria J. Rodriguez, Luis Fernando Temoche, Pavlos Protopapas

The authors test a physics-informed neural network for solving static Kerr perturbation equations and extracting tidal responses. Comparing extraction on network and exact solutions reveals contamination in a local derivative method. In the benchmark, an H2 loss yields relative solution error 9.97×10^-5, versus 2.33×10^-1 with H1 loss. The result is limited to static Kerr perturbations and does not establish vanishing conservative response.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.