Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ

DOI10.1142/S0219530518500203zbMATH Open1478.68309OpenAlexW2883486956WikidataQ129516912 ScholiaQ129516912MaRDI QIDQ4615657FDOQ4615657

Authors: Christoph Schwab, J. Zech 

Publication date: 29 January 2019

Published in: Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219530518500203

Recommendations

• Deep learning in high dimension: ReLU neural network expression for Bayesian PDE inversion
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
• Deep neural network expression of posterior expectations in Bayesian PDE inversion
• Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients

zbMATH Keywords

uncertainty quantificationsparse gridsgeneralized polynomial chaosdeep networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• Inverse problems: a Bayesian perspective
• Analytic regularity and polynomial approximation of parametric and stochastic elliptic PDE's
• High-dimensional adaptive sparse polynomial interpolation and applications to parametric PDEs
• Multilayer feedforward networks are universal approximators
• Title not available (Why is that?)
• Convergence rates of best \(N\)-term Galerkin approximations for a class of elliptic SPDEs
• Title not available (Why is that?)
• Convergence rates of multilevel and sparse tensor approximations for a random elliptic PDE
• Approximation of high-dimensional parametric PDEs
• Analyticity in infinite dimensional spaces
• Sparse deterministic approximation of Bayesian inverse problems
• Numerical solution of parametrized Navier–Stokes equations by reduced basis methods
• Breaking the curse of dimensionality in sparse polynomial approximation of parametric PDEs
• Sparse polynomial approximation of parametric elliptic PDEs. Part I: affine coefficients
• Title not available (Why is that?)
• Multilevel approximation of parametric and stochastic PDES
• Fully discrete approximation of parametric and stochastic elliptic PDEs
• Electromagnetic wave scattering by random surfaces: shape holomorphy
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Error bounds for approximations with deep ReLU networks
• Differential operators on domains with conical points: precise uniform regularity estimates
• Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
• Optimal approximation with sparsely connected deep neural networks
• Multilevel higher-order quasi-Monte Carlo Bayesian estimation
• Shape holomorphy of the stationary Navier-Stokes equations
• Deep vs. shallow networks: an approximation theory perspective
• Convergence rates of high dimensional Smolyak quadrature

Cited In (78)

• Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models
• Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
• Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
• Title not available (Why is that?)
• CAS4DL: Christoffel adaptive sampling for function approximation via deep learning
• Constructive deep ReLU neural network approximation
• Approximation rates for neural networks with encodable weights in smoothness spaces
• Solving parametric partial differential equations with deep rectified quadratic unit neural networks
• DNN expression rate analysis of high-dimensional PDEs: application to option pricing
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• Exponential Convergence of Deep Operator Networks for Elliptic Partial Differential Equations
• Non-Intrusive Reduced Order Modeling of Convection Dominated Flows Using Artificial Neural Networks with Application to Rayleigh-Taylor Instability
• Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
• Sparse polynomial approximations for affine parametric saddle point problems
• The Random Feature Model for Input-Output Maps between Banach Spaces
• Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• On the approximation of functions by tanh neural networks
• Deep ReLU neural networks in high-dimensional approximation
• Balanced joint maximum mean discrepancy for deep transfer learning
• Deep learning in high dimension: ReLU neural network expression for Bayesian PDE inversion
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
• Numerical solution of the parametric diffusion equation by deep neural networks
• Model reduction and neural networks for parametric PDEs
• Deep neural network expression of posterior expectations in Bayesian PDE inversion
• Stein variational gradient descent with local approximations
• Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
• ReLU neural network Galerkin BEM
• Convergence rate of DeepONets for learning operators arising from advection-diffusion equations
• Surrogate modeling for Bayesian inverse problems based on physics-informed neural networks
• Neural network approximation and estimation of classifiers with classification boundary in a Barron class
• De Rham compatible deep neural network FEM
• Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
• Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
• Multilevel approximation of parametric and stochastic PDES
• Robust randomized optimization with \(k\) nearest neighbors
• Data-driven forward discretizations for Bayesian inversion
• Deep neural network surrogates for nonsmooth quantities of interest in shape uncertainty quantification
• Deep learning-based approximation of Goldbach partition function
• Nonlinear approximation and (deep) ReLU networks
• Domain uncertainty quantification in computational electromagnetics
• A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
• Title not available (Why is that?)
• Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs
• A theoretical analysis of deep neural networks and parametric PDEs
• Higher-order quasi-Monte Carlo training of deep neural networks
• The gap between theory and practice in function approximation with deep neural networks
• Data driven approximation of parametrized PDEs by reduced basis and neural networks
• Simultaneous neural network approximation for smooth functions
• An adaptive surrogate modeling based on deep neural networks for large-scale Bayesian inverse problems
• Exponential ReLU neural network approximation rates for point and edge singularities
• Deep Learning in High Dimension: Neural Network Expression Rates for Analytic Functions in \(\pmb{L^2(\mathbb{R}^d,\gamma_d)}\)
• Deep ReLU networks and high-order finite element methods
• Error analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEs
• Full error analysis for the training of deep neural networks
• Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs
• Optimal approximation of infinite-dimensional holomorphic functions
• Deep ReLU networks and high-order finite element methods. II: Chebyšev emulation
• Operator learning using random features: a tool for scientific computing
• Error analysis for deep neural network approximations of parametric hyperbolic conservation laws
• One-shot learning of surrogates in PDE-constrained optimization under uncertainty
• Wavenumber-Explicit Parametric Holomorphy of Helmholtz Solutions in the Context of Uncertainty Quantification
• Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
• Neural and spectral operator surrogates: unified construction and expression rate bounds
• Multilevel domain uncertainty quantification in computational electromagnetics
• On the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysis
• Probabilistic partition of unity networks for high‐dimensional regression problems
• On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fields
• Energy-dissipative evolutionary deep operator neural networks
• Parametric shape holomorphy of boundary integral operators with applications
• Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics
• wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws
• Error assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDE
• Exploiting locality in sparse polynomial approximation of parametric elliptic PDEs and application to parameterized domains
• Learning high frequency data via the coupled frequency predictor-corrector triangular DNN
• Adaptive operator learning for infinite-dimensional Bayesian inverse problems
• Convergence Rates for Learning Linear Operators from Noisy Data
• Limitations of neural network training due to numerical instability of backpropagation
• Neural network expression rates and applications of the deep parametric PDE method in counterparty credit risk

This page was built for publication: Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4615657)