Learning Partial Differential Equations by Spectral Approximates of General Sobolev Spaces

We introduce a novel spectral, finite-dimensional approximation of general Sobolev spaces in terms of Chebyshev polynomials. Based on this polynomial surrogate model (PSM), we realise a variational formulation, solving a vast class of linear and non-linear partial differential equations (PDEs). The PSMs are as flexible as the physics-informed neural nets (PINNs) and provide an alternative for addressing inverse PDE problems, such as PDE-parameter inference. In contrast to PINNs, the PSMs result in a convex optimisation problem for a vast class of PDEs, including all linear ones, in which case the PSM-approximate is efficiently computable due to the exponential convergence rate of the underlying variational gradient descent. As a practical consequence prominent PDE problems were resolved by the PSMs without High Performance Computing (HPC) on a local machine. This gain in efficiency is complemented by an increase of approximation power, outperforming PINN alternatives in both accuracy and runtime. Beyond the empirical evidence we give here, the translation of classic PDE theory in terms of the Sobolev space approximates suggests the PSMs to be universally applicable to well-posed, regular forward and inverse PDE problems.

READ FULL TEXT

page 12

page 13

page 14

research
11/27/2019

Variational Physics-Informed Neural Networks For Solving Partial Differential Equations

Physics-informed neural networks (PINNs) [31] use automatic differentiat...
research
05/10/2022

Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools

We introduce the Optimizing a Discrete Loss (ODIL) framework for the num...
research
05/18/2022

Modeling complex root motion of real random polynomials under differentiation

In this paper, we consider nonlocal, nonlinear partial differential equa...
research
07/09/2019

PDE/PDF-informed adaptive sampling for efficient non-intrusive surrogate modelling

A novel refinement measure for non-intrusive surrogate modelling of part...
research
02/22/2021

NTopo: Mesh-free Topology Optimization using Implicit Neural Representations

Recent advances in implicit neural representations show great promise wh...
research
01/20/2022

Derivative-informed projected neural network for large-scale Bayesian optimal experimental design

We address the solution of large-scale Bayesian optimal experimental des...

Please sign up or login with your details

Forgot password? Click here to reset