The Random Feature Model for Input-Output Maps between Banach Spaces

Abstract

Well known to the machine learning community, the random feature model is a parametric approximation to kernel interpolation or regression methods. It is typically used to approximate functions mapping a finite-dimensional input space to the real line. In this paper, we instead propose a methodology for use of the random feature model as a data-driven surrogate for operators that map an input Banach space to an output Banach space. Although the methodology is quite general, we consider operators defined by partial differential equations (PDEs); here, the inputs and outputs are themselves functions, with the input parameters being functions required to specify the problem, such as initial data or coefficients, and the outputs being solutions of the problem. Upon discretization, the model inherits several desirable attributes from this infinite-dimensional viewpoint, including mesh-invariant approximation error with respect to the true PDE solution map and the capability to be trained at one mesh resolution and then deployed at different mesh resolutions. We view the random feature model as a non-intrusive data-driven emulator, provide a mathematical framework for its interpretation, and demonstrate its ability to efficiently and accurately approximate the nonlinear parameter-to-solution maps of two prototypical PDEs arising in physical science and engineering applications: viscous Burgers' equation and a variable coefficient elliptic equation.

To appear in SIAM Journal on Scientific Computing; 32 pages, 9 figures

References in corpus (8)

• Fourier Neural Operator for Parametric Partial Differential Equations
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis
• A physics-informed operator regression framework for extracting data-driven continuum models
• FiniteNet: A Fully Convolutional LSTM Network Architecture for Time-Dependent Partial Differential Equations
• Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
• Blow up and regularity for fractal Burgers equation
• Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data

Cited by in corpus (17)

• Fourier Neural Operator for Parametric Partial Differential Equations
• Multipole Graph Neural Operator for Parametric Partial Differential Equations
• Calibration and Uncertainty Quantification of Convective Parameters in an Idealized GCM
• Choose a Transformer: Fourier or Galerkin
• A Kernel Two-Sample Test for Functional Data
• Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks
• Catch-22s of reservoir computing
• Convergence Rates for Learning Linear Operators from Noisy Data
• Solving and Learning Nonlinear PDEs with Gaussian Processes
• Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory
• Learning phase field mean curvature flows with neural networks
• SPADE4: Sparsity and Delay Embedding based Forecasting of Epidemics
• Improve Unscented Kalman Inversion With Low-Rank Approximation and Reduced-Order Model
• Extreme learning machines for variance-based global sensitivity analysis
• Asymptotic Consistency for Nonconvex Risk-Averse Stochastic Optimization with Infinite Dimensional Decision Spaces
• Learning Partial Differential Equations in Reproducing Kernel Hilbert Spaces
• Discovering Hidden Physics Behind Transport Dynamics