arXiv：cs.AI· Lucas Thil, Jesse Read, Guillaume Doquet, Rim Kaddah·· 5 小时前
SPLICE：稀疏物理算子库识别与组合式扩展
SPLICE: Sparse Physics Library Identification and Compositional Expansion
AI 导读
SPLICE 框架可在无机制标签的混合数据中发现神经算子，并通过求解凸优化问题推断候选算子对每条轨迹的贡献，再用校准测试为每个算子分配其实现的物理机制。在一维和二维系统上，发现的算子可从无标签混合数据中还原机制，并零样本组合成未见方程的模拟器；冻结的算子库还能在无标签、不遗忘的前提下为预训练中缺失的物理机制新增算子。在 Navier-Stokes 上，其组合精度与有监督版本相当。
正文
Abstract:Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations. Existing approaches, however, require these mechanisms and their labels to be specified in advance. We ask whether a pretrained library can instead be adapted and grown from unlabeled trajectories in which multiple mechanisms act simultaneously. We introduce SPLICE, a framework that discovers operators without mechanism labels on mixture data. The contributions of the candidate operators to each trajectory are inferred by solving a convex optimization problem. A calibrated test then assigns each discovered operator the mechanism it implements. Failure cases are also detectable, when the library lacks the required physics or when mechanisms are insufficiently separable. Across one and two dimensional systems, the discovered operators recover mechanisms from unlabeled mixtures and compose into zero-shot simulators of unseen equations; a frozen library can also grow an operator for physics absent from pretraining, without labels and without forgetting. On Navier-Stokes, the discovered operators compose about as accurately as their supervised counterparts.
| Comments: | 24 pages, 6 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17029 [cs.LG] |
| (or arXiv:2610.17029v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17029 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lucas Thil [view email]
[v1]
Mon, 12 Oct 2026 16:07:06 UTC (1,199 KB)
来源：arXiv：cs.AI · arxiv.org