提出一种基于泛函线性回归的数据驱动方法,在再生核 Hilbert 空间中学习线性偏微分方程的 Green 函数,通过表示定理降维并扩展预测误差理论,在多种方程上验证了其抗噪性与泛化能力。
摘要:
我们提出了一种新的数据驱动方法,用于在给定输入-输出函数样本对的情况下,学习各种线性偏微分方程(PDEs)的基本解(Green函数)。基于泛函线性回归(FLR)理论,我们在再生核 Hilbert 空间(RKHS)中估计基本解的最佳拟合 Green 函数和偏置项,这使我们能够对其平滑性进行正则化并施加各种结构约束。我们推导了算子 RKHS 的一般表示定理,通过有限维问题来近似原始的无限维回归问题,将搜索空间缩小到 Green 函数的参数类。为了研究我们的 Green 函数估计器的预测误差,我们将先前关于标量输出 FLR 的结果扩展到具有函数输出的情况。最后,我们在几个线性 PDE 上演示了我们的方法,包括 Poisson、Helmholtz、Schrödinger、Fokker-Planck 和热方程。我们强调了它对噪声的鲁棒性,以及在无需任何额外训练的情况下,泛化到具有不同平滑度和网格离散化程度的新数据的能力。
英文摘要:
We propose a new data-driven approach for learning the fundamental solutions (Green's functions) of various linear partial differential equations (PDEs) given sample pairs of input-output functions. Building off the theory of functional linear regression (FLR), we estimate the best-fit Green's function and bias term of the fundamental solution in a reproducing kernel Hilbert space (RKHS) which allows us to regularize their smoothness and impose various structural constraints. We derive a general representer theorem for operator RKHSs to approximate the original infinite-dimensional regression problem by a finite-dimensional one, reducing the search space to a parametric class of Green's functions. In order to study the prediction error of our Green's function estimator, we extend prior results on FLR with scalar outputs to the case with functional outputs. Finally, we demonstrate our method on several linear PDEs including the Poisson, Helmholtz, Schrödinger, Fokker-Planck, and heat equation. We highlight its robustness to noise as well as its ability to generalize to new data with varying degrees of smoothness and mesh discretization without any additional training.
Reproducing kernel Hilbert spaces on manifolds: Sobolev and Diffusion spaces
Universita’ degli Studi di Genova(热那亚大学);University of Stuttgart(斯图加特大学);Massachusetts Institute of Technology(麻省理工学院);Istituto Italiano di Tecnologia(意大利理工学院)
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces
McGill University(麦吉尔大学);Mila - Quebec Artificial Intelligence Institute(魁北克人工智能研究所(Mila));Université du Québec à Montréal(魁北克大学蒙特利尔分校);Facebook AI Research(Facebook人工智能研究);CIFAR AI chair(CIFAR人工智能主席职位);DeepMind;Université de Montréal(蒙特利尔大学)