Metraipolis › archive › dc_52fffb29e2d6

A fast, differentiable neural-network surrogate for precessing binary black-hole waveforms — arXiv:2608.09978

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09978
License (as archived)
CC0-1.0
Archived
2026-10-19T06:41:44.902Z
SHA-256 of the archived text
8c3f2e3e9395a9f3b2615d27d15d6d3e25a4e5dd1722df61e76b51b9f521ba16
Stable URL of this page
https://metraipolis.com/documento/dc_52fffb29e2d6

How to cite

A fast, differentiable neural-network surrogate for precessing binary black-hole waveforms — arXiv:2608.09978 — arXiv (en), https://arxiv.org/abs/2608.09978 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_52fffb29e2d6 (Metraipolis archive dc_52fffb29e2d6, sha256 8c3f2e3e9395a9f3b2615d27d15d6d3e25a4e5dd1722df61e76b51b9f521ba16)
BibTeX
@misc{dc52fffb29e2d6,
  title = {A fast, differentiable neural-network surrogate for precessing binary black-hole waveforms — arXiv:2608.09978},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09978},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_52fffb29e2d6; sha256 8c3f2e3e9395a9f3b2615d27d15d6d3e25a4e5dd1722df61e76b51b9f521ba16},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09978. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Gravitational-wave parameter estimation requires millions of waveform evaluations per event, a cost that constrains real-time inference and population studies. We present a fast, fully differentiable neural-network surrogate for the precessing numerical-relativity model \NRSur{}, spanning its full intrinsic parameter space $\lambda=(q,\,\boldsymbol{\chi}_1,\,\boldsymbol{\chi}_2)$ together with the reference orbital frequency $\omega_0$. Rather than a single polarization at a fixed orientation, the surrogate predicts the \emph{inertial-frame spherical-harmonic modes} $h_{\ell m}$ ($\ell\leq 4$), so that both polarizations $h_+,h_\times$ at an arbitrary orientation $(\iota,\varphi,\psi)$ are reconstructed from one network evaluation through an analytic, differentiable mode-to-strain projection. Trained on $6\times10^5$ waveforms, it attains a fixed-orientation match of mean $0.975$ (median $0.988$) and an orientation-averaged match of mean $0.940$ (median $0.975$) for $q\in[1,4]$, $|\boldsymbol{\chi}_{1,2}|\leq 0.8$, while keeping the overall strain amplitude physical (median ratio $0.98$). It generates a waveform in $\SI{12}{ms}$ (single) and ${\sim}3.5\times10^4$ per second in batches on a single GPU. Because the mode-to-strain projection is analytic, the surrogate is differentiable in both intrinsic and extrinsic parameters, yielding a full 13-dimensional Fisher matrix (validated against finite differences) and gradient-based (HMC/NUTS) parameter estimation.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-08-12 in astro-ph.IM).
Categorie arXiv: General Relativity and Quantum Cosmology (gr-qc) ; High Energy Astrophysical Phenomena (astro-ph.HE); Instrumentation and Methods for Astrophysics (astro-ph.IM).
Pagina del lavoro: https://arxiv.org/abs/2608.09978 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:37:00.857Z dalla pagina https://arxiv.org/catchup/astro-ph.IM/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).