Solving inverse problems using data-driven models

DOI10.1017/S0962492919000059zbMath1429.65116OpenAlexW2952020389MaRDI QIDQ5230520

Ozan Öktem, Carola-Bibiane Schönlieb, Peter Maass, Simon R. Arridge

Publication date: 28 August 2019

Published in: Acta Numerica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1017/s0962492919000059

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Research exposition (monographs, survey articles) pertaining to numerical analysis (65-02) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items

Convergence Results for Primal-Dual Algorithms in the Presence of Adjoint Mismatch, A Fast Data-Driven Iteratively Regularized Method with Convex Penalty for Solving Ill-Posed Problems, On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector, Phase computation for the finite-genus solutions to the focusing nonlinear Schrödinger equation using convolutional neural networks, Dynamical Systems–Based Neural Networks, Application of machine learning regression models to inverse eigenvalue problems, Bayesian synergistic metamodeling (BSM) for physical information infused data-driven metamodeling, Tomographic inverse problems: mathematical challenges and novel applications. Abstracts from the workshop held April 30 -- May 5, 2023, On the determination of Lagrange multipliers for a weighted Lasso problem using geometric and convex analysis techniques, Hierarchical ensemble Kalman methods with sparsity-promoting generalized gamma hyperpriors, Solving inverse problems with deep learning, On mathematical modeling in image reconstruction and beyond, A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors, High-resolution signal recovery via generalized sampling and functional principal component analysis, Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method, Adversarially learned iterative reconstruction for imaging inverse problems, The numerics of phase retrieval, Learning physics-based models from data: perspectives from inverse problems and model reduction, Fast Bayesian inversion for high dimensional inverse problems, Cauchy Markov random field priors for Bayesian inversion, Regularization theory of the analytic deep prior approach, WARPd: A Linearly Convergent First-Order Primal-Dual Algorithm for Inverse Problems with Approximate Sharpness Conditions, Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting), Deep microlocal reconstruction for limited-angle tomography, Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint, A new hybrid regularization scheme for removing salt and pepper noise, Two-Layer Neural Networks with Values in a Banach Space, Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction, Discretization of parameter identification in PDEs using neural networks, Inverse problems on low-dimensional manifolds, Consistency of Bayesian inference with Gaussian process priors for a parabolic inverse problem, Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion, A Generative Variational Model for Inverse Problems in Imaging, Model order reduction method based on (r)POD-ANNs for parameterized time-dependent partial differential equations, A probabilistic approach to tomography and adjoint state methods, with an application to full waveform inversion in medical ultrasound, Neural networks for classification of strokes in electrical impedance tomography on a 3D head model, Designing rotationally invariant neural networks from PDEs and variational methods, Task adapted reconstruction for inverse problems, An efficient algorithm to compute the X-ray transform, Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie, Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks, Inverse medium scattering problems with Kalman filter techniques, Learning spectral windowing parameters for regularization using unbiased predictive risk and generalized cross validation techniques for multiple data sets, Bilevel inverse problems in neuromorphic imaging, Stein Variational Gradient Descent on Infinite-Dimensional Space and Applications to Statistical Inverse Problems, Short Communication: Localized Adversarial Artifacts for Compressed Sensing MRI, Divide-and-conquer DNN approach for the inverse point source problem using a few single frequency measurements, Variational regularization in inverse problems and machine learning, Deep learning methods for partial differential equations and related parameter identification problems, Learning-informed parameter identification in nonlinear time-dependent PDEs, A data-driven Kaczmarz iterative regularization method with non-smooth constraints for ill-posed problems, Fully probabilistic deep models for forward and inverse problems in parametric PDEs, Convergence Rates for Learning Linear Operators from Noisy Data, Joint Reconstruction-Segmentation on Graphs, In focus -- hybrid deep learning approaches to the HDC2021 challenge, Restoring severely out-of-focus blurred text images with deep image prior, Let's enhance: a deep learning approach to extreme deblurring of text images, Limitations of neural network training due to numerical instability of backpropagation, Extraction of Digital Wavefront Sets Using Applied Harmonic Analysis and Deep Neural Networks, A Note on the Regularity of Images Generated by Convolutional Neural Networks, A direct sampling-based deep learning approach for inverse medium scattering problems, Invertible residual networks in the context of regularization theory for linear inverse problems, A Data-Assisted Two-Stage Method for the Inverse Random Source Problem, Sequential Model Correction for Nonlinear Inverse Problems, The Split Gibbs Sampler Revisited: Improvements to Its Algorithmic Structure and Augmented Target Distribution, Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling, Regularising inverse problems with generative machine learning models, On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent, Explainable bilevel optimization: an application to the Helsinki Deblur Challenge, On and Beyond Total Variation Regularization in Imaging: The Role of Space Variance, Deep learning for inverse problems with unknown operator, A novel physics-informed framework for reconstruction of structural defects, Applied harmonic analysis and data science. Abstracts from the workshop held November 28 -- December 4, 2021 (hybrid meeting), Consistency of Bayesian inference with Gaussian process priors in an elliptic inverse problem, Data-consistent neural networks for solving nonlinear inverse problems, NESTANets: stable, accurate and efficient neural networks for analysis-sparse inverse problems, Computed tomography reconstruction using deep image prior and learned reconstruction methods, Classification of stroke using neural networks in electrical impedance tomography, Joint super-resolution image reconstruction and parameter identification in imaging operator: analysis of bilinear operator equations, numerical solution, and application to magnetic particle imaging, Data driven regularization by projection, Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method, Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach Part I: Methodology and Experiments, An introduction to finite element methods for inverse coefficient problems in elliptic PDEs, Non-stationary multi-layered Gaussian priors for Bayesian inversion, Regularization by architecture: a deep prior approach for inverse problems, Learning regularization parameters of inverse problems via deep neural networks, Posterior consistency of semi-supervised regression on graphs, Unnamed Item, GAN-Based Priors for Quantifying Uncertainty in Supervised Learning, Inexact derivative-free optimization for bilevel learning, Constructive deep ReLU neural network approximation, Infinite-dimensional inverse problems with finite measurements, Multilevel Markov Chain Monte Carlo for Bayesian Inversion of Parabolic Partial Differential Equations under Gaussian Prior, Summary statistics and discrepancy measures for approximate Bayesian computation via surrogate posteriors, Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network, The Gap between Theory and Practice in Function Approximation with Deep Neural Networks, Purity assessment of pellets using deep learning, Hybrid projection methods for large-scale inverse problems with mixed Gaussian priors, Variational Bayes' Method for Functions with Applications to Some Inverse Problems, Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data, On Learned Operator Correction in Inverse Problems, Deep Neural Networks for Inverse Problems with Pseudodifferential Operators: An Application to Limited-Angle Tomography, Structure-preserving deep learning, Compressive sensing and neural networks from a statistical learning perspective, High resolution 3D ultrasonic breast imaging by time-domain full waveform inversion, Unsupervised knowledge-transfer for learned image reconstruction*, Approximation of discontinuous inverse operators with neural networks, Constrained and unconstrained deep image prior optimization models with automatic regularization, Optimization with learning-informed differential equation constraints and its applications, Deep learning architectures for nonlinear operator functions and nonlinear inverse problems, Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

Uses Software

Cites Work