A machine learning framework for data driven acceleration of computations of differential equations

DOI10.3934/Mine.2018.1.118zbMath1435.68279arXiv1807.09519OpenAlexW2884714875WikidataQ128931094 ScholiaQ128931094MaRDI QIDQ2305115

Siddhartha Mishra

Publication date: 10 March 2020

Published in: Mathematics in Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.09519

zbMATH Keywords

nonconvex optimizationdifferential equationsmachine learningdeep learningtime-dependent problems

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Finite difference methods for initial value and initial-boundary value problems involving PDEs (65M06) Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Numerical methods for initial value problems involving ordinary differential equations (65L05) Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08)

Related Items

A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations ⋮ Hyperbolic balance laws: modeling, analysis, and numerics. Abstracts from the workshop held February 28 -- March 6, 2021 (hybrid meeting) ⋮ Mean-field and kinetic descriptions of neural differential equations ⋮ On the numerical discretization of a tumor progression model driven by competing migration mechanisms ⋮ Neural control of discrete weak formulations: Galerkin, least squares \& minimal-residual methods with quasi-optimal weights ⋮ Accelerating algebraic multigrid methods via artificial neural networks ⋮ Continuous limits of residual neural networks in case of large input data ⋮ Learning Optimal Multigrid Smoothers via Neural Networks ⋮ Learning the nonlinear flux function of a hidden scalar conservation law from data ⋮ A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms ⋮ Identification of the flux function of nonlinear conservation laws with variable parameters ⋮ An artificial neural network approach to identify the parameter in a nonlinear subdiffusion model ⋮ A machine learning approach to enhance the SUPG stabilization method for advection-dominated differential problems ⋮ Artificial neural network approximations of Cauchy inverse problem for linear PDEs ⋮ Iterative surrogate model optimization (ISMO): an active learning algorithm for PDE constrained optimization with deep neural networks ⋮ A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations ⋮ Deep learning observables in computational fluid dynamics ⋮ Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences ⋮ A priori and a posteriori error estimates for the deep Ritz method applied to the Laplace and Stokes problem ⋮ A multi-level procedure for enhancing accuracy of machine learning algorithms ⋮ DNN expression rate analysis of high-dimensional PDEs: application to option pricing

Uses Software

• Matlab
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-level Monte Carlo finite volume methods for nonlinear systems of conservation laws in multi-dimensions
• Hidden physics models: machine learning of nonlinear partial differential equations
• Multilayer feedforward networks are universal approximators
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Error bounds for approximations with deep ReLU networks
• An artificial neural network as a troubled-cell indicator
• Inverse problems: A Bayesian perspective
• Arbitrarily High-order Accurate Entropy Stable Essentially Nonoscillatory Schemes for Systems of Conservation Laws
• Computational Optimization of Systems Governed by Partial Differential Equations
• Universal approximation bounds for superpositions of a sigmoidal function
• Entropy stability theory for difference approximations of nonlinear conservation laws and related time-dependent problems
• Spectral Methods in MATLAB
• The Mathematical Theory of Finite Element Methods