PDE-constrained Models with Neural Network Terms: Optimization and Global Convergence

by   Justin Sirignano, et al.

Recent research has used deep learning to develop partial differential equation (PDE) models in science and engineering. The functional form of the PDE is determined by a neural network, and the neural network parameters are calibrated to available data. Calibration of the embedded neural network can be performed by optimizing over the PDE. Motivated by these applications, we rigorously study the optimization of a class of linear elliptic PDEs with neural network terms. The neural network parameters in the PDE are optimized using gradient descent, where the gradient is evaluated using an adjoint PDE. As the number of parameters become large, the PDE and adjoint PDE converge to a non-local PDE system. Using this limit PDE system, we are able to prove convergence of the neural network-PDE to a global minimum during the optimization. The limit PDE system contains a non-local linear operator whose eigenvalues are positive but become arbitrarily small. The lack of a spectral gap for the eigenvalues poses the main challenge for the global convergence proof. Careful analysis of the spectral decomposition of the coupled PDE and adjoint PDE system is required. Finally, we use this adjoint method to train a neural network model for an application in fluid mechanics, in which the neural network functions as a closure model for the Reynolds-averaged Navier-Stokes (RANS) equations. The RANS neural network model is trained on several datasets for turbulent channel flow and is evaluated out-of-sample at different Reynolds numbers.



There are no comments yet.


page 7


DPM: A deep learning PDE augmentation method (with application to large-eddy simulation)

Machine learning for scientific applications faces the challenge of limi...

Neural Q-learning for solving elliptic PDEs

Solving high-dimensional partial differential equations (PDEs) is a majo...

Frame-independent vector-cloud neural network for nonlocal constitutive modelling on arbitrary grids

Constitutive models are widely used for modelling complex systems in sci...

Sparse Hierarchical Preconditioners Using Piecewise Smooth Approximations of Eigenvectors

When solving linear systems arising from PDE discretizations, iterative ...

Constrained Image Generation Using Binarized Neural Networks with Decision Procedures

We consider the problem of binary image generation with given properties...

DeepPropNet – A Recursive Deep Propagator Neural Network for Learning Evolution PDE Operators

In this paper, we propose a deep neural network approximation to the evo...

Anomaly detection and classification for streaming data using PDEs

Nondominated sorting, also called Pareto Depth Analysis (PDA), is widely...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.