Metraipolis › archive › dc_3853835dd10e
WaSP: Wasserstein Data Synthesis Pipeline for Solver-Free Operator Learning — arXiv:2611.07646
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07646
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:42:31.438Z
- SHA-256 of the archived text
4892772ca4d72a5ac598580e867539238d60efd63c384ac60def71e7808445e8- Stable URL of this page
https://metraipolis.com/documento/dc_3853835dd10e
How to cite
WaSP: Wasserstein Data Synthesis Pipeline for Solver-Free Operator Learning — arXiv:2611.07646 — arXiv (en), https://arxiv.org/abs/2611.07646 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3853835dd10e (Metraipolis archive dc_3853835dd10e, sha256 4892772ca4d72a5ac598580e867539238d60efd63c384ac60def71e7808445e8)
BibTeX
@misc{dc3853835dd10e,
title = {WaSP: Wasserstein Data Synthesis Pipeline for Solver-Free Operator Learning — arXiv:2611.07646},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07646},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3853835dd10e; sha256 4892772ca4d72a5ac598580e867539238d60efd63c384ac60def71e7808445e8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07646. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural operators offer fast surrogates for solving PDEs, but training them typically requires expensive input-solution pairs. Two solver-free alternatives include physics-informed learning and training on manufactured data. Physics-informed learning approximates solutions by minimizing PDE residuals. While the residual norm must be strong enough to control solution error, stronger norms increase mini-batch variance and hinder optimization. Manufactured data constructs input-solution pairs for learning by applying the PDE operator to artificial solutions. However, the resulting training distribution can be mutually singular with the target distribution, yielding poor accuracy on the target distribution. We introduce the Wasserstein Data Synthesis Pipeline (WaSP), which trains on manufactured input-solution pairs while gradually mitigating the distribution shift. WaSP synthesizes new pairs by applying the learned operator to a path of intermediate distributions converging to the target input distribution. Training proceeds in stages along this path. At each stage, the previous surrogate generates solutions, and the exact PDE operator derives corresponding inputs, yielding training pairs for the next surrogate. Theoretically, we prove a stepwise error-propagation bound for the distribution shift introduced during synthesis. Empirically, WaSP reduces solution error by $3.9\times$ to $9.5\times$ compared to existing solver-free methods on PDEs such as Allen-Cahn, Kuramoto-Sivashinsky, and Ginzburg-Landau, and better reproduces the two chaotic systems' statistical observables. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.07646 — 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 2026-11-06T14:18:42.682Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).