Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
From MaRDI portal
Publication:2026114
DOI10.1007/s10444-020-09834-7zbMath1472.65134arXiv2001.11441OpenAlexW3126658681MaRDI QIDQ2026114
Philipp Petersen, Fabian Laakmann
Publication date: 18 May 2021
Published in: Advances in Computational Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2001.11441
Artificial neural networks and deep learning (68T07) Neural networks for/in biological studies, artificial life and related topics (92B20) Theoretical approximation in context of PDEs (35A35) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99) Transport equations (35Q49)
Related Items
A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations ⋮ On the approximation of functions by tanh neural networks ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Model-order reduction for hyperbolic relaxation systems ⋮ Exponential ReLU neural network approximation rates for point and edge singularities ⋮ Neural network approximation and estimation of classifiers with classification boundary in a Barron class ⋮ Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting) ⋮ Numerical solution of the parametric diffusion equation by deep neural networks ⋮ Model reduction and neural networks for parametric PDEs ⋮ POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition ⋮ CAS4DL: Christoffel adaptive sampling for function approximation via deep learning ⋮ Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Reduced order methods for modeling and computational reduction
- Ordinary differential equations, transport theory and Sobolev spaces
- Partial differential equations. 3rd ed
- Adaptive anisotropic Petrov-Galerkin methods for first order transport equations
- Multilayer feedforward networks are universal approximators
- Provable approximation properties for deep neural networks
- The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
- On the approximation of functions with line singularities by ridgelets
- Approximation properties of a multilayered feedforward artificial neural network
- DGM: a deep learning algorithm for solving partial differential equations
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- Approximation of infinitely differentiable multivariate functions is intractable
- Error bounds for approximations with deep ReLU networks
- A MIXED VARIATIONAL FRAMEWORK FOR THE RADIATIVE TRANSFER EQUATION
- Certified Reduced Basis Methods for Parametrized Partial Differential Equations
- Matrix Analysis
- Universal approximation bounds for superpositions of a sigmoidal function
- Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ
- An adaptive nested source term iteration for radiative transfer equations
- Optimal Approximation with Sparsely Connected Deep Neural Networks
- Deep ReLU networks and high-order finite element methods
- Error bounds for approximations with deep ReLU neural networks in Ws,p norms
- Efficient Resolution of Anisotropic Structures
- Double greedy algorithms: Reduced basis methods for transport dominated problems
- On the Theory of Dynamic Programming
- Ordinary Differential Equations
- Approximation by superpositions of a sigmoidal function
