Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
Summary: We develop a theoretical analysis for special neural network architectures, termed \textit{operator recurrent neural networks}, for approximating nonlinear functions whose inputs are linear operators. Such functions commonly arise in solution algorithms for inverse boundary value problems. Traditional neural networks treat input data as vectors, and thus they do not effectively capture the multiplicative structure associated with the linear operators that correspond to the data in such inverse problems. We therefore introduce a new family that resembles a standard neural network architecture, but where the input data acts multiplicatively on vectors. Motivated by compact operators appearing in boundary control and the analysis of inverse boundary value problems for the wave equation, we promote structure and sparsity in selected weight matrices in the network. After describing this architecture, we study its representation properties as well as its approximation properties. We furthermore show that an explicit regularization can be introduced that can be derived from the mathematical analysis of the mentioned inverse problems, and which leads to certain guarantees on the generalization properties. We observe that the sparsity of the weight matrices improves the generalization estimates. Lastly, we discuss how operator recurrent networks can be viewed as a deep learning analogue to deterministic algorithms such as boundary control for reconstructing the unknown wave speed in the acoustic wave equation from boundary measurements.
- Deep learning for inverse problems with unknown operator
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- Convolutional Neural Networks in Phase Space and Inverse Problems
- NETT: solving inverse problems with deep neural networks
- Big in Japan: regularizing networks for solving inverse problems
- A global uniqueness theorem for an inverse boundary value problem
- A Lipschitz stable reconstruction formula for the inverse problem for the wave equation
- A representer theorem for deep neural networks
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Boundary regularity for the Ricci equation, geometric convergence, and Gel'fand's inverse boundary problem
- Boundary rigidity and filling volume minimality of metrics close to a flat one
- Boundary rigidity with partial data
- Consistency of Bayesian inference with Gaussian process priors in an elliptic inverse problem
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Deep learning for photoacoustic tomography from sparse data
- Discrete regularization and convergence of the inverse problem for 1+1 dimensional wave equation
- Equivalence of time-domain inverse problems and boundary spectral problems
- Error bounds for approximations with deep ReLU networks
- scientific article; zbMATH DE number 1713116 (Why is no real title available?)
- scientific article; zbMATH DE number 1022519 (Why is no real title available?)
- scientific article; zbMATH DE number 1022658 (Why is no real title available?)
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- Inverse boundary value problems for partial differential equations
- Inverse problem for the Riemannian wave equation with Dirichlet data and Neumann data on disjoint sets
- Inverse problems for linear and non-linear hyperbolic equations
- Inverse problems for Lorentzian manifolds and non-linear hyperbolic equations
- Iterative time-reversal control for inverse problems
- Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography
- Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
- Multiscale sparse microcanonical models
- NETT: solving inverse problems with deep neural networks
- Networks for nonlinear diffusion problems in imaging
- On statistical Calderón problems
- Probability Inequalities for Sums of Bounded Random Variables
- Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness
- Reconstruction of piecewise smooth wave speeds using multiple scattering
- Recovery of a smooth metric via wave field and coordinate transformation reconstruction
- Regularization strategy for an inverse problem for a \(1 + 1\) dimensional wave equation
- Scattering control for the wave equation with unknown wave speed
- Semiglobal boundary rigidity for Riemannian metrics
- Solving an inverse obstacle problem for the wave equation by using the boundary control method
- Solving ill-posed inverse problems using iterative deep neural networks
- Solving inverse problems using data-driven models
- Splines are universal solutions of linear inverse problems with generalized TV regularization
- Stability estimates for the anisotropic wave equation from the Dirichlet-to-Neumann map
- Stability estimates for the hyperbolic Dirichlet to Neumann map in anisotropic media
- Stability For a Multidimensional Inverse Spectral Theorem
- Statistical guarantees for Bayesian uncertainty quantification in nonlinear inverse problems with Gaussian process priors
- SwitchNet: a neural Network Model for forward and inverse scattering problems
- Theory and applications of time reversal and interferometric imaging
- Time Reversal and Refocusing in Random Media
- To the reconstruction of a riemannian manifold via its spectral data (Bc–Method)
- Two dimensional compact simple Riemannian manifolds are boundary distance rigid
- Improved architectures and training algorithms for deep operator networks
- BCR-net: A neural network based on the nonstandard wavelet form
- Data-consistent neural networks for solving nonlinear inverse problems
- Inverse problems on low-dimensional manifolds
- Convergence Rates for Learning Linear Operators from Noisy Data
- A Data-Assisted Two-Stage Method for the Inverse Random Source Problem
- The Calderón's problem via DeepONets
- Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation
- MCMC-Net: accelerating Markov chain Monte Carlo with neural networks for inverse problems
- The learned range test method for the inverse inclusion problem
- Forward and Backward Problems for Coupled Subdiffusion Systems
- Neural operators can play dynamic Stackelberg games
- Designing universal causal deep learning models: the case of infinite-dimensional dynamical systems from stochastic analysis
This page was built for publication: Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2113263)
