NETT: solving inverse problems with deep neural networks
From MaRDI portal
Publication:5113628
Abstract: Recovering a function or high-dimensional parameter vector from indirect measurements is a central task in various scientific areas. Several methods for solving such inverse problems are well developed and well understood. Recently, novel algorithms using deep learning and neural networks for inverse problems appeared. While still in their infancy, these techniques show astonishing performance for applications like low-dose CT or various sparse data problems. However, there are few theoretical results for deep learning in inverse problems. In this paper, we establish a complete convergence analysis for the proposed NETT (Network Tikhonov) approach to inverse problems. NETT considers data consistent solutions having small value of a regularizer defined by a trained neural network. We derive well-posedness results and quantitative error estimates, and propose a possible strategy for training the regularizer. Our theoretical results and framework are different from any previous work using neural networks for solving inverse problems. A possible data driven regularizer is proposed. Numerical results are presented for a tomographic sparse data problem, which demonstrate good performance of NETT even for unknowns of different type from the training data. To derive the convergence and convergence rates results we introduce a new framework based on the absolute Bregman distance generalizing the standard Bregman distance from the convex to the non-convex case.
Recommendations
- Big in Japan: regularizing networks for solving inverse problems
- Solving ill-posed inverse problems using iterative deep neural networks
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- Deep learning for trivial inverse problems
- Deep learning for inverse problems with unknown operator
Cites work
- scientific article; zbMATH DE number 2156763 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- rm K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
- A Tikhonov-based projection iteration for nonlinear ill-posed problems with sparsity con\-straints
- A wavelet tour of signal processing. The sparse way.
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Convergence rates and source conditions for Tikhonov regularization with sparsity constraints
- Convergence rates of convex variational regularization
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Deep learning
- Deep learning for photoacoustic tomography from sparse data
- Dictionary Identification—Sparse Matrix-Factorization via \ell₁-Minimization
- Generalized Bregman distances and convergence rates for non-convex regularization methods
- Inversion of Spherical Means and the Wave Equation in Even Dimensions
- Mathematical methods in image reconstruction
- Mathematics of thermoacoustic tomography
- Necessary and sufficient conditions for linear convergence of ^1-regularization
- New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities
- Orthonormal bases of compactly supported wavelets
- Photoacoustic and thermoacoustic tomography: image formation principles
- Proximal splitting methods in signal processing
- Sampling Conditions for the Circular Radon Transform
- Solving ill-posed inverse problems using iterative deep neural networks
- Sparse regularization with l q penalty term
- Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors
- The Little Engine that Could: Regularization by Denoising (RED)
- The residual method for regularizing ill-posed problems
- Totally convex functions for fixed points computation and infinite dimensional optimization
- Variational methods in imaging
Cited in
(only showing first 100 items - show all)- Adversarially learned iterative reconstruction for imaging inverse problems
- Deep learning for trivial inverse problems
- Big in Japan: regularizing networks for solving inverse problems
- Networks for nonlinear diffusion problems in imaging
- ADMM based Fourier phase retrieval with untrained generative prior
- Deep unrolling networks with recurrent momentum acceleration for nonlinear inverse problems
- Solving high-dimensional inverse problems using amortized likelihood-free inference with noisy and incomplete data
- Learnable descent algorithm for nonsmooth nonconvex image reconstruction
- Constructing probing functions for direct sampling methods for inverse scattering problems with limited-aperture data: finite space framework and deep probing network
- Deep learning methods for partial differential equations and related parameter identification problems
- A data-dependent regularization method based on the graph Laplacian
- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- The numerics of phase retrieval
- Strong Solutions for PDE-Based Tomography by Unsupervised Learning
- Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
- Uncertainty quantification for goal-oriented inverse problems via variational encoder-decoder networks
- Stability of data-dependent ridge-regularization for inverse problems
- A guide to stochastic optimisation for large-scale inverse problems
- A direct sampling-based deep learning approach for inverse medium scattering problems
- DRIP: deep regularizers for inverse problems
- Wide-band butterfly network: stable and efficient inversion via multi-frequency neural networks
- The Calderón's problem via DeepONets
- Convergent data-driven regularizations for CT reconstruction
- Alpert multi-wavelets for functional inverse problems: direct optimization and deep learning
- Convolutional Neural Networks in Phase Space and Inverse Problems
- On obtaining initial approximation for the full wave inversion problem using convolutional neural network
- Jacobi stability and restoration of parameters of the nonlinear double pendulum
- Shared Prior Learning of Energy-Based Models for Image Reconstruction
- An accelerated inexact Newton regularization scheme with a learned feature-selection rule for non-linear inverse problems
- Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
- Regularising inverse problems with generative machine learning models
- TNet: A Model-Constrained Tikhonov Network Approach for Inverse Problems
- Deep convolutional framelets: a general deep learning framework for inverse problems
- Rethinking the ill-posedness of the spectral function reconstruction -- why is it fundamentally hard and how artificial neural networks can help
- Analytic continuation of noisy data using Adams Bashforth residual neural network
- Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting)
- Training adaptive reconstruction networks for blind inverse problems
- A mathematical framework for deep learning in elastic source imaging
- Convergence and recovery guarantees of unsupervised neural networks for inverse problems
- Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography
- Wasserstein-based projections with applications to inverse problems
- Gauss-Newton method for solving linear inverse problems with neural network coders
- Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction
- Bregman methods for large-scale optimization with applications in imaging
- Bilevel optimization methods in imaging
- Deep learning methods for limited data problems in X-ray tomography
- Learned regularizers for inverse problems
- Regularization of inverse problems by neural networks
- Early stopping of untrained convolutional neural networks
- Divide-and-conquer DNN approach for the inverse point source problem using a few single frequency measurements
- Convergence analysis of critical point regularization with non-convex regularizers
- Improvements on uncertainty quantification with variational autoencoders
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
- Application of machine learning regression models to inverse eigenvalue problems
- NESTANets: stable, accurate and efficient neural networks for analysis-sparse inverse problems
- Iteratively Refined Image Reconstruction with Learned Attentive Regularizers
- Learning sparsity-promoting regularizers for linear inverse problems
- A paired autoencoder framework for inverse problems via Bayes risk minimization
- Neural networks for Bayesian inverse problems governed by a nonlinear ODE
- Learning two parameters in fractional Tikhonov regularization method via deep neural networks: application to the inverse problem for the Laplace operator with noisy data
- Multi-layer 5D optical data storage: mathematical modeling and deep learning-based reconstruction of birefringent parameters
- Deep null space learning for inverse problems: convergence analysis and rates
- Bayesian view on the training of invertible residual networks for solving linear inverse problems
- Deep learning for inverse problems with unknown operator
- Quadratic Neural Networks for Solving Inverse Problems
- Numerical methods for identifying the diffusion coefficient in a nonlinear elliptic equation
- Solving inverse problems with deep learning
- Oracle-net for nonlinear compressed sensing in electrical impedance tomography reconstruction problems
- Solving Bayesian inverse problems using neural networks
- Proximal neural networks and stochastic normalizing flows for inverse problems
- Why the noise model matters: a performance gap in learned regularization
- Approximation of discontinuous inverse operators with neural networks
- Regularization theory of the analytic deep prior approach
- Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion
- Deep synthesis network for regularizing inverse problems
- On the convergence of the iterative regularization method assisted by the graph Laplacian with early stopping
- A primal-dual algorithm for image reconstruction with input-convex neural network regularizers
- Learning regularization parameters of inverse problems via deep neural networks
- Relaxation approach for learning neural network regularizers for a class of identification problems
- Normalizing flow regularization for photoacoustic tomography
- A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction
- Hybrid projection methods for large-scale inverse problems with mixed Gaussian priors
- Parseval proximal neural networks
- Compressive sensing and neural networks from a statistical learning perspective
- Convergent regularization in inverse problems and linear plug-and-play denoisers
- Data-Driven Morozov Regularization of Inverse Problems
- Solving ill-posed inverse problems using iterative deep neural networks
- Learning spiking neuronal networks with artificial neural networks: neural oscillations
- Computed tomography reconstruction using deep image prior and learned reconstruction methods
- An adaptively inexact method for bilevel learning using primal-dual-style differentiation
- Stability bounds for the unfolded forward-backward algorithm
- Invertible residual networks in the context of regularization theory for linear inverse problems
- Neural-network-based regularization methods for inverse problems in imaging
- Data driven regularization by projection
- Learnable Douglas-Rachford iteration and its applications in DOT imaging
- Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
- Data-consistent neural networks for solving nonlinear inverse problems
- Solving an inverse source problem by deep neural network method with convergence and error analysis
- Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network
This page was built for publication: NETT: solving inverse problems with deep neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5113628)
