Deep neural network expression of posterior expectations in Bayesian PDE inversion

DOI10.1088/1361-6420/abaf64zbMath1453.35191OpenAlexW3049518590MaRDI QIDQ5139333

J. Zech, Lukas Herrmann, Christoph Schwab

Publication date: 8 December 2020

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1088/1361-6420/abaf64

zbMATH Keywords

exponential convergenceuncertainty quantificationBayesian inverse problemsapproximation ratesdeep ReLU neural networks

Mathematics Subject Classification ID

Boundary value problems for second-order elliptic equations (35J25) Inverse problems for PDEs (35R30)

Related Items

Rank Bounds for Approximating Gaussian Densities in the Tensor-Train Format, On Bayesian data assimilation for PDEs with ill-posed forward problems, Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification, On the approximation of functions by tanh neural networks, Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs, Stability estimates for the expected utility in Bayesian optimal experimental design, Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs, Convergence rates for ansatz‐free data‐driven inference in physically constrained problems, Constructive deep ReLU neural network approximation, Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks, Exponential ReLU DNN expression of holomorphic maps in high dimension

Cites Work

• A Bayesian level set method for geometric inverse problems
• Besov priors for Bayesian inverse problems
• A formula for the tail probability of a multivariate normal distribution and its applications
• On statistical Calderón problems
• Functional analysis, Sobolev spaces and partial differential equations
• The inhomogeneous Dirichlet problem in Lipschitz domains
• On the Lebesgue constant of Leja sequences for the complex unit disk and of their real projection
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Higher order quasi-Monte Carlo integration for Bayesian PDE inversion
• Discretization-invariant Bayesian inversion and Besov space priors
• Error bounds for approximations with deep ReLU networks
• On some generalizations of a theorem of A. Markoff
• Multilevel Higher Order QMC Petrov--Galerkin Discretization for Affine Parametric Operator Equations
• Sparse, adaptive Smolyak quadratures for Bayesian inverse problems
• Complexity analysis of accelerated MCMC methods for Bayesian inversion
• Sparse deterministic approximation of Bayesian inverse problems
• Multilevel higher-order quasi-Monte Carlo Bayesian estimation
• Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ
• Functional Analysis
• Multilevel approximation of parametric and stochastic PDES
• Analysis of a multilevel Markov chain Monte Carlo finite element method for Bayesian inversion of log-normal diffusions
• Multilevel Quasi-Monte Carlo Uncertainty Quantification for Advection-Diffusion-Reaction
• Deep ReLU networks and high-order finite element methods
• High order approximation of probabilistic shock profiles in hyperbolic conservation laws with uncertain initial data
• Adaptive Finite Element Methods for Elliptic Problems with Discontinuous Coefficients
• Front tracking for hyperbolic conservation laws
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item