Metraipolis › archive › dc_e6622e18f2eb

Meshless Latent Dynamics Models for Model Order Reduction of time-dependent Partial Differential Equations — arXiv:2610.41043

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41043
License (as archived)
CC0-1.0
Archived
2026-11-03T08:12:48.819Z
SHA-256 of the archived text
0d91a4ed8194c76d2aff38dafbf457b6e07bdcb5d18749ff9de00d8fe761ce6a
Stable URL of this page
https://metraipolis.com/documento/dc_e6622e18f2eb

How to cite

Meshless Latent Dynamics Models for Model Order Reduction of time-dependent Partial Differential Equations — arXiv:2610.41043 — arXiv (en), https://arxiv.org/abs/2610.41043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6622e18f2eb (Metraipolis archive dc_e6622e18f2eb, sha256 0d91a4ed8194c76d2aff38dafbf457b6e07bdcb5d18749ff9de00d8fe761ce6a)
BibTeX
@misc{dce6622e18f2eb,
  title = {Meshless Latent Dynamics Models for Model Order Reduction of time-dependent Partial Differential Equations — arXiv:2610.41043},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41043},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6622e18f2eb; sha256 0d91a4ed8194c76d2aff38dafbf457b6e07bdcb5d18749ff9de00d8fe761ce6a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Latent dynamics learning has emerged as a prominent approach for Model Order Reduction (MOR) of time-dependent, parameterized Partial Differential Equations (PDEs). Traditional autoencoder-based approaches are intrinsically tied to fixed spatial discretizations during both training and inference, motivating the development of meshless methodologies. In this context, conditioning provides a natural mechanism for representing temporal evolution through spatially continuous functions, enabling mesh-agnostic Latent Dynamics Models (LDMs). In this work, we introduce a unified mathematical framework for mesh-agnostic LDMs based on conditioning in Neural Fields (NeFs). Leveraging a taxonomy of conditioning mechanisms (weak, strong, and pure), we formulate meshless LDMs as NeFs conditioned on a latent state. We establish a Universal Approximation Theorem (UAT) for this class of models and analyze their stability by deriving Lipschitz bounds for different conditioning mechanisms. Our analysis reveals an expressivity--stability trade-off, providing insight into why more expressive conditioning, despite its higher representational capacity, can potentially degrade performance during temporal extrapolation. Finally, we provide a comprehensive comparison of meshless and mesh-based architectures in the continuous limit of the spatial discretization, showing that meshless models guarantee grid-independent Lipschitz bounds, unlike mesh-based counterparts. Our experiments across Burgers' equation, Navier--Stokes flow past a cylinder, and linear advection show that meshless LDMs can achieve predictive accuracy comparable to or better than their mesh-based counterparts while using only 2% of the trainable parameters and exhibiting nearly constant error across spatial discretizations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41043 — 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 2026-11-03T08:02:38.973Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).