Geometric Neural Operators via Lie Group-Constrained Latent Dynamics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915803899625472 |
|---|---|
| author | Zhang, Jiaquan Puspitasari, Fachrina Dewi Zhang, Songbo Liu, Yibei Liu, Kuien Qin, Caiyan Mo, Fan Wang, Peng Yang, Yang Zhang, Chaoning |
| author_facet | Zhang, Jiaquan Puspitasari, Fachrina Dewi Zhang, Songbo Liu, Yibei Liu, Kuien Qin, Caiyan Mo, Fan Wang, Peng Yang, Yang Zhang, Chaoning |
| contents | Neural operators offer an effective framework for learning solutions of partial differential equations for many physical systems in a resolution-invariant and data-driven manner. Existing neural operators, however, often suffer from instability in multi-layer iteration and long-horizon rollout, which stems from the unconstrained Euclidean latent space updates that violate the geometric and conservation laws. To address this challenge, we propose to constrain manifolds with low-rank Lie algebra parameterization that performs group action updates on the latent representation. Our method, termed Manifold Constraining based on Lie group (MCL), acts as an efficient \emph{plug-and-play} module that enforces geometric inductive bias to existing neural operators. Extensive experiments on various partial differential equations, such as 1-D Burgers and 2-D Navier-Stokes, over a wide range of parameters and steps demonstrate that our method effectively lowers the relative prediction error by 30-50\% at the cost of 2.26\% of parameter increase. The results show that our approach provides a scalable solution for improving long-term prediction fidelity by addressing the principled geometric constraints absent in the neural operator updates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16209 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Geometric Neural Operators via Lie Group-Constrained Latent Dynamics Zhang, Jiaquan Puspitasari, Fachrina Dewi Zhang, Songbo Liu, Yibei Liu, Kuien Qin, Caiyan Mo, Fan Wang, Peng Yang, Yang Zhang, Chaoning Machine Learning Artificial Intelligence Neural operators offer an effective framework for learning solutions of partial differential equations for many physical systems in a resolution-invariant and data-driven manner. Existing neural operators, however, often suffer from instability in multi-layer iteration and long-horizon rollout, which stems from the unconstrained Euclidean latent space updates that violate the geometric and conservation laws. To address this challenge, we propose to constrain manifolds with low-rank Lie algebra parameterization that performs group action updates on the latent representation. Our method, termed Manifold Constraining based on Lie group (MCL), acts as an efficient \emph{plug-and-play} module that enforces geometric inductive bias to existing neural operators. Extensive experiments on various partial differential equations, such as 1-D Burgers and 2-D Navier-Stokes, over a wide range of parameters and steps demonstrate that our method effectively lowers the relative prediction error by 30-50\% at the cost of 2.26\% of parameter increase. The results show that our approach provides a scalable solution for improving long-term prediction fidelity by addressing the principled geometric constraints absent in the neural operator updates. |
| title | Geometric Neural Operators via Lie Group-Constrained Latent Dynamics |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.16209 |