Metraipolis › archive › dc_a358e4950652
Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems — arXiv:2608.17344
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17344
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:31:26.443Z
- SHA-256 of the archived text
9c7a58709a5527210bdeaeae8543500af9c0a147c93361fb252adef3739b3833- Stable URL of this page
https://metraipolis.com/documento/dc_a358e4950652
How to cite
Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems — arXiv:2608.17344 — arXiv (en), https://arxiv.org/abs/2608.17344 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a358e4950652 (Metraipolis archive dc_a358e4950652, sha256 9c7a58709a5527210bdeaeae8543500af9c0a147c93361fb252adef3739b3833)
BibTeX
@misc{dca358e4950652,
title = {Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems — arXiv:2608.17344},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17344},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a358e4950652; sha256 9c7a58709a5527210bdeaeae8543500af9c0a147c93361fb252adef3739b3833},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17344. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural network surrogates are an emerging alternative to traditional electromagnetic wave simulators like finite-difference time-domain (FDTD); their goal is to replace rigorous physical simulations with pre-trained neural networks that solve wave-scattering forward and inverse problems orders of magnitude faster. However, nonrecurrent, single-step surrogates have scaled only to a few tens of simulation variables. Here, we show that this barrier can be overcome by dynamically generating salient training examples during training, rather than randomly sampling the large space of possible examples. We introduce an algorithm that runs in parallel with surrogate training, using gradient ascent to search refractive-index and source configurations for cases where the surrogate disagrees with a full-wave ground-truth simulator. We also use source and ground-truth normalization with an evolving replay dataset to stabilize and accelerate learning. Using this approach, we train a fast, single-step surrogate for two-dimensional wave scattering with up to 41,772 controllable variables, including dense, freely configurable grids of refractive indices and complex-valued sources. The resulting neural surrogate is robustly accurate across diverse structured and unstructured examples and generalizes inductively to larger domains, reaching over 3 million controllable variables without retraining, a $73.8\times$ increase. We demonstrate the surrogate on large-scale forward simulations and inverse design of freeform beam splitters and gradient-index (GRIN) lenses up to 98 wavelengths wide, showing comparable or better performance than FDTD-based designs, with speedups from $1.29\times$ to $26.5\times$. These results demonstrate a practical path toward fast, robustly accurate, inductively scalable neural simulators for photonic inverse design and other wave-scattering inverse problems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI). Categorie arXiv: Optics (physics.optics) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.17344 — 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 2026-10-18T14:27:54.420Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).