论文

TangentPDE:用稀疏有限差分监督学习神经 PDE 算子的局部响应

TangentPDE: Learning Local Operator Responses with Sparse Finite-Difference Supervision

精选理由

训练神经 PDE 算子的人可以看看这篇。它只用稀疏配对输入的状态输出就能构造监督信号,不用伴随求解和雅可比矩阵,在 20 个设置里 18 个降了误差,即插即用接各种算子骨干。

一篇 arXiv 论文提出 TangentPDE,一种神经 PDE 算子的训练框架,用有限差分近似方向导数,从参考求解器在稀疏配对输入上的状态输出构造任务相关的有限步响应标签。其目标函数同时约束状态保真度、响应方向对齐和响应幅值校准,因此同时学习算子取值与局部变化。

正文

该方法的核心优势在于标签完全由配对输入的状态输出构造,不需要显式导数标签、线性化或伴随 PDE 求解,也不需要完整雅可比矩阵,可以直接用于没有导数接口的非线性求解器。论文还提出一种选择性执行的自适应机制,在有限差分监督下强化局部算子表征。通过预算匹配和对应关系扰动两组对照实验,作者分离出关系监督本身带来的提升。

实验覆盖 4 个 PDE 系统和 20 个任务-骨干组合,TangentPDE 在其中 18 个设置上降低了三种子平均状态误差,18 个设置上降低了 Rollout@20 误差。该方法设计为即插即用的训练框架,可接入多种神经算子骨干,内在有限步响应增益在 DiffReact 上最强,其余场景依任务和骨干而定。

原文 · arXiv cs.LG

TangentPDE: Learning Local Operator Responses with Sparse Finite-Difference Supervision

Neural PDE operators are often optimized through state reconstruction, which largely constrains operator values at observed inputs but does not fully characterize their sensitivity to local perturbations. A more faithful approximation of operator behavior requires not only accurate state predictions, but also correct variations along local perturbation directions. We present TangentPDE, which uses finite differences to approximate directional derivatives and constructs task-relevant finite-step responses from the state outputs of a reference solver at sparse paired inputs. Its objective jointly constrains state fidelity, response-direction alignment, and response-magnitude calibration, thereby learning both operator values and their local variations. Because the response labels are constructed solely from state outputs at paired inputs, the method requires neither explicit derivative labels, linearized or adjoint PDE solves, nor full Jacobians, and remains applicable to nonlinear solvers without derivative interfaces. Building on this, we additionally propose a selectively executed adaptation mechanism to strengthen local operator representations under finite-difference supervision. Budget-matched and correspondence-perturbed controls isolate the effect of relational supervision from improvements attributable to additional state observations or increased data volume. Designed as a plug-and-play training framework, TangentPDE integrates with diverse neural-operator backbones. Across four PDE systems and 20 task-backbone settings, TangentPDE lowers the three-seed mean state error in 18 settings and the corresponding Rollout@20 error in 18, while intrinsic finite-step response gains are strongest on DiffReact and remain task- and backbone-dependent elsewhere.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:神经算子、PDE求解、有限差分、TangentPDE,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Xinjian Xie, Ruxuan Chen, Jiashu Li, Tianyu Gao, Ye Wei),经 AITOP 多维评分管线结构化提炼。