SageNet: Fast Neural Network Emulation of the Stiff-amplified Gravitational Waves from Inflation

Abstract

Accurate modeling of the inflationary gravitational waves (GWs) requires time-consuming, iterative numerical integrations of differential equations to take into account their backreaction on the expansion history. To improve computational efficiency while preserving accuracy, we present SageNet (Stiff-Amplified Gravitational-wave Emulator Network), a deep learning framework designed to replace conventional numerical solvers. SageNet employs a Long Short-Term Memory architecture to emulate the present-day energy density spectrum of the inflationary GWs with possible stiff amplification, $\Omega_\mathrm{GW}(f)$. Trained on a data set of 25,689 numerically generated solutions, SageNet allows accurate reconstructions of $\Omega_\mathrm{GW}(f)$ and generalizes well to a wide range of cosmological parameters; 89.3% of the test emulations with randomly distributed parameters exhibit errors of under 4%. In addition, SageNet demonstrates its ability to learn and reproduce the artificial, adaptive sampling patterns in numerical calculations, which implement denser sampling of frequencies around changes of spectral indices in $\Omega_\mathrm{GW}(f)$. The dual capability of learning both physical and artificial features of the numerical GW spectra establishes SageNet as a robust alternative to exact numerical methods. Finally, our benchmark tests show that SageNet reduces the computation time from tens of seconds to milliseconds, achieving a speed-up of ~$10^4$ times over standard CPU-based numerical solvers with the potential for further acceleration on GPU hardware. These capabilities make SageNet a powerful tool for accelerating Bayesian inference procedures for extended cosmological models. In a broad sense, the SageNet framework offers a fast, accurate, and generalizable solution to modeling cosmological observables whose theoretical predictions demand costly differential equation solvers.