Metraipolis › archive › dc_bc45eb54fe3a

From Numerical Simulators of PDEs to Neural Emulators and Back — arXiv:2608.24547

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24547
License (as archived)
CC0-1.0
Archived
2026-10-18T06:36:16.121Z
SHA-256 of the archived text
24fb189d479ca52684e6a3b11978b2ce790a50205037b9091b16babad8507ae0
Stable URL of this page
https://metraipolis.com/documento/dc_bc45eb54fe3a

How to cite

From Numerical Simulators of PDEs to Neural Emulators and Back — arXiv:2608.24547 — arXiv (en), https://arxiv.org/abs/2608.24547 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc45eb54fe3a (Metraipolis archive dc_bc45eb54fe3a, sha256 24fb189d479ca52684e6a3b11978b2ce790a50205037b9091b16babad8507ae0)
BibTeX
@misc{dcbc45eb54fe3a,
  title = {From Numerical Simulators of PDEs to Neural Emulators and Back — arXiv:2608.24547},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24547},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc45eb54fe3a; sha256 24fb189d479ca52684e6a3b11978b2ce790a50205037b9091b16babad8507ae0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24547. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simulation is central to modern engineering and science, but the cost of numerical solvers for partial differential equations (PDEs) remains a bottleneck whenever fast or many-query evaluations are required. Neural emulators trained on solver-generated data promise significant speedups, yet they are usually framed as opaque alternatives to the very methods that produce their training signal. This thesis argues the two paradigms are more alike than different: neural architectures mirror classical discretizations, their errors are amenable to the same spectral analysis, and insight flows profitably in both directions. We approach the relationship by disentangling the multiple roles a solver plays in the emulator learning pipeline. Mode-wise Fourier analysis then provides a common language in which solver errors, architectural inductive biases, and training objectives can all be read off simultaneously. Taken together, this allows synthesizing three contributions. (1) APEBench, a comprehensive benchmarking suite for autoregressive neural emulators of PDEs that uses fast differentiable pseudo-spectral solvers in JAX. (2) Progressively Refined Differentiable Physics, an investigation of the effect of unconverged solvers on surrogate training. (3) Neural Emulator Superiority, an analysis of the influence of numerical errors and architectural inductive biases.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.24547 — 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 2026-10-18T06:28:52.254Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).