Neural Galerkin Scheme with Active Learning for High-Dimensional Evolution Equations

03/02/2022
by   Joan Bruna, et al.
9

Machine learning methods have been shown to give accurate predictions in high dimensions provided that sufficient training data are available. Yet, many interesting questions in science and engineering involve situations where initially no data are available and the principal aim is to gather insights from a known model. Here we consider this problem in the context of systems whose evolution can be described by partial differential equations (PDEs). We use deep learning to solve these equations by generating data on-the-fly when and where they are needed, without prior information about the solution. The proposed Neural Galerkin schemes derive nonlinear dynamical equations for the network weights by minimization of the residual of the time derivative of the solution, and solve these equations using standard integrators for initial value problems. The sequential learning of the weights over time allows for adaptive collection of new input data for residual estimation. This step uses importance sampling informed by the current state of the solution, in contrast with other machine learning methods for PDEs that optimize the network parameters globally in time. This active form of data acquisition is essential to enable the approximation power of the neural networks and to break the curse of dimensionality faced by non-adaptative learning strategies. The applicability of the method is illustrated on several numerical examples involving high-dimensional PDEs, including advection equations with many variables, as well as Fokker-Planck equations for systems with several interacting particles.

READ FULL TEXT

page 7

page 10

page 21

page 22

research
09/12/2022

Numerical approximation based on deep convolutional neural network for high-dimensional fully nonlinear merged PDEs and 2BSDEs

In this paper, we propose two efficient approximation methods to solve h...
research
06/27/2023

Coupling parameter and particle dynamics for adaptive sampling in Neural Galerkin schemes

Training nonlinear parametrizations such as deep neural networks to nume...
research
05/10/2023

Global Convergence of Deep Galerkin and PINNs Methods for Solving Partial Differential Equations

Numerically solving high-dimensional partial differential equations (PDE...
research
12/28/2021

Active Learning Based Sampling for High-Dimensional Nonlinear Partial Differential Equations

The deep-learning-based least squares method has shown successful result...
research
06/01/2022

Discrete Gradient Flow Approximations of High Dimensional Evolution Partial Differential Equations via Deep Neural Networks

We consider the approximation of initial/boundary value problems involvi...
research
07/10/2023

Galerkin-Bernstein Approximations of the System of Time Dependent Nonlinear Parabolic PDEs

The purpose of the research is to find the numerical solutions to the sy...
research
05/30/2023

Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs

Solving partial differential equations (PDEs) is a central task in scien...

Please sign up or login with your details

Forgot password? Click here to reset