A theoretical analysis of deep neural networks and parametric PDEs

From MaRDI portal
Publication:2117329

DOI10.1007/s00365-021-09551-4OpenAlexW3167031531WikidataQ114229767 ScholiaQ114229767MaRDI QIDQ2117329

Mones Raslan, Philipp Petersen, Gitta Kutyniok, Reinhold Schneider

Publication date: 21 March 2022

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1904.00377




Related Items (46)

Linear/ridge expansions: enhancing linear approximations by ridge functionsReduced basis methods for time-dependent problemsA Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential EquationsA neural network multigrid solver for the Navier-Stokes equationsTwo-Layer Neural Networks with Values in a Banach SpaceDiscretization of parameter identification in PDEs using neural networksA deep learning approach to Reduced Order Modelling of parameter dependent partial differential equationsDeep neural network approximations for solutions of PDEs based on Monte Carlo algorithmsOvercoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearitiesVariational physics informed neural networks: the role of quadratures and test functionsApproximations with deep neural networks in Sobolev time-spaceDesigning rotationally invariant neural networks from PDEs and variational methodsFull error analysis for the training of deep neural networksUnbiased Deep Solvers for Linear Parametric PDEsDeep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty QuantificationDeep ReLU neural network approximation in Bochner spaces and applications to parametric PDEsDeep Surrogate Accelerated Delayed-Acceptance Hamiltonian Monte Carlo for Bayesian Inference of Spatio-Temporal Heat Fluxes in Rotating Disc SystemsAn introduction to the mathematics of deep learningNeural Network Approximation of Coarse-Scale Surrogates in Numerical HomogenizationDeep learning methods for partial differential equations and related parameter identification problemsMesh-informed neural networks for operator learning in finite element spacesSparse polynomial approximations for affine parametric saddle point problemsA New Certified Hierarchical and Adaptive RB-ML-ROM Surrogate Model for Parametrized PDEsLearning high frequency data via the coupled frequency predictor-corrector triangular DNNExponential Convergence of Deep Operator Networks for Elliptic Partial Differential EquationsSpace-time error estimates for deep neural network approximations for differential equationsLimitations of neural network training due to numerical instability of backpropagationDeep convolutional Ritz method: parametric PDE surrogates without labeled dataCollocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputsConnections between numerical algorithms for PDEs and neural networksAn artificial neural network approach to bifurcating phenomena in computational fluid dynamicsDeepBND: a machine learning approach to enhance multiscale solid mechanicsLearning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricingOn the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysisDNN-MG: a hybrid neural network/finite element method with applications to 3D simulations of the Navier-Stokes equationsA machine learning approach to enhance the SUPG stabilization method for advection-dominated differential problemswPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation LawsThe mathematics of artificial intelligenceError assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDEComputation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting)Approximation properties of residual neural networks for Kolmogorov PDEsAn overview on deep learning-based approximation methods for partial differential equationsSolving traveltime tomography with deep learningUnnamed ItemSolving parametric partial differential equations with deep rectified quadratic unit neural networksPDE-Aware Deep Learning for Inverse Problems in Cardiac Electrophysiology


Uses Software


Cites Work


This page was built for publication: A theoretical analysis of deep neural networks and parametric PDEs