The Interpolating Neural Operator (INO) is proposed, a data-free interpolating neural network that is trained directly on the weak form of the PDE, and is compared with physics-informed FNO and DeepONet on different benchmarks.
Abstract
Neural operators have become a popular approach to approximate the solution operators of parametric partial differential equations (PDEs). However, existing neural operators either require a large amount of simulation data or a long physics-informed training on GPUs, and they cannot tell how accurate an individual prediction is. In this paper, we propose the Interpolating Neural Operator (INO), a data-free interpolating neural network that is trained directly on the weak form of the PDE. In INO, the Karhunen-Lo\`eve coordinates of the input field are treated as additional inputs together with the spatial coordinates, and each input is approximated by a C-HiDeNN sub-network whose trainable parameters are nodal values. Since the network is multilinear in its parameters, training reduces to a sequence of one-dimensional linear solves by greedy alternating least squares. As a result, INO trains on one CPU core and predicts a new solution in microseconds. For coercive problems, the total error of every prediction is bounded by a computable residual bound that requires no reference solution, and the same bound applies to the predictions of other methods that satisfy the boundary conditions exactly. Before each prediction, INO checks whether the leading coordinates of the input lie within the range on which it is trained, and inputs outside this range can be passed to a conventional solver or to an INO trained on a wider range. INO is compared with physics-informed FNO and DeepONet on different benchmarks. INO is the most accurate model on most of these problems, by 15$\times$ on two-dimensional Helmholtz at $65^2$ and 53$\times$ on the diffusion-reaction benchmark, and on the one- and two-dimensional problems its training on one CPU core takes 3-80$\times$ less time than the physics-informed baselines on one GPU.
Neural operators are typically trained in a supervised fashion, which requires a dataset to be generated with a classical solver. Training them physics-informed, i.e., purely from the governing equations, removes this large offline cost and allows fresh samples to be drawn at every optimization step, but has so far bee...
Shi-Zheng Wen, Siddhartha Mishra, Marius Zeinhofer· arXiv.org· 1 citation
L-SplineFNO, a memory-efficient neural operator that couples an FNO backbone with a sparse, learnable tensor-product B-spline transfer between unstructured meshes and a latent Cartesian grid, achieves strong predictive accuracy while requiring substantially less memory and compute than baseline operators.
Vignesh Gopakumar, Zhuoyuan Wang, Ander Gray et al.· 0 citations
Operator learning aims to learn mappings between function spaces and has been widely used for PDE-related problems. This raises two fundamental questions. First, is there a connection between standard numerical methods and neural operators, given that both are designed to approximate PDE solution operators? Second, whe...
This work investigates PolyNets that couple a continuous-time neural representation of polynomial dynamics with a simple recurrent network for discrete-time integration and achieves accuracy comparable to the numerical solvers, including at amplitudes outside the learned models'training conditions.
L. Todorović, Kaushal Gianchandani, S. Ravela· 0 citations
This paper presents a comparative study of classical numerical and machine learning techniques for solving the nonlinear Monge–Ampère Equation (MAE). A finite difference method (FDM) implemented in MATLAB is first validated using a quadratic exact solution on a square domain. Two neural network approaches are then inve...
Christopher Ogbonna, Maliki Olaniyi S, N. Ogbonna· International journal of re...· 0 citations
We present a local and sparse kernel method for learning the solution operators of incompressible flows. It builds on our earlier property-preserving kernel method, whose global output reconstruction and dense operator regression scale poorly. Our method replaces the global output reconstruction by local divergence-fre...
Ramansh Sharma, Matthew Lowery, H. Owhadi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.