Metraipolis › archive › dc_e1643da71b0f

Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver — arXiv:2609.24021

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24021
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:42.051Z
SHA-256 of the archived text
0de675c7d371055817f4f1e84554374ec2dface2af183255217de1879b2311a6
Stable URL of this page
https://metraipolis.com/documento/dc_e1643da71b0f

How to cite

Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver — arXiv:2609.24021 — arXiv (en), https://arxiv.org/abs/2609.24021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1643da71b0f (Metraipolis archive dc_e1643da71b0f, sha256 0de675c7d371055817f4f1e84554374ec2dface2af183255217de1879b2311a6)
BibTeX
@misc{dce1643da71b0f,
  title = {Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver — arXiv:2609.24021},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24021},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1643da71b0f; sha256 0de675c7d371055817f4f1e84554374ec2dface2af183255217de1879b2311a6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural operators are data-driven models that learn mappings from inputs that parameterize partial differential equations, such as spatially varying coefficients, initial conditions, forcing terms, boundary conditions, or geometries, to solution fields or quantities of interest. Once trained, they can serve as surrogates for classical numerical solvers in many-query settings that require repeated evaluations for varying inputs. We address the question of when, and then why, neural operator surrogates outperform classical numerical solvers, in terms of cost for a given accuracy. We focus on the post-training, many-query limit, in which data-acquisition and training costs are treated as fixed and fully amortized. Even in this deliberately favorable regime for neural operators, there are regimes in which classical solvers outperform the surrogate models. We compare the cost-accuracy performance of neural operator surrogates and classical numerical solvers through a reproducible benchmark study comparing neural operators with problem-matched classical solvers on representative problems in computational science and engineering, focusing on prediction error, per-query floating-point cost, and wall-clock runtime. Neural operators are most competitive at low-to-moderate accuracy requirements. Their floating-point cost advantage depends strongly on the problem structure, arising when they avoid temporal or nonlinear iterations or predict a reduced quantity of interest rather than a full solution field. Additional wall-clock speedups result from dense tensor operations that are well suited to modern hardware. As the target accuracy is tightened, achieving the required accuracy with neural operators becomes increasingly challenging, and classical solvers outperform surrogates in this regime; thus classical solvers will remain important for verification and high-accuracy computation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.24021 — 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 2026-10-09T06:58:09.622Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).