Deep learning for inverse problems with unknown operator

Publication date: 13 March 2023

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2108.02744

zbMATH Keywords

inverse problems; nonparametric statistics; convolutional neural networks; deep learning; unknown operator

Mathematics Subject Classification ID

62G05: Nonparametric estimation

68T07: Artificial neural networks and deep learning

65J22: Numerical solution to inverse problems in abstract spaces

Uses Software

U-Net

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Sparse recovery under matrix uncertainty
Variance estimation for high-dimensional regression models
Nonparametric methods for inference in the presence of instrumental variables
Minimax goodness-of-fit testing in ill-posed inverse problems with partially unknown operators
Minimax estimation via wavelet shrinkage
Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
Nonparametric regression using deep neural networks with ReLU activation function
Error bounds for approximations with deep ReLU networks
Universality of deep convolutional neural networks
On deep learning as a remedy for the curse of dimensionality in nonparametric regression
Maximum entropy solution to ill-posed inverse problems with approximately known operator
Nonlinear estimation for linear inverse problems with error in the operator
Adaptive estimation for an inverse regression model with unknown operator
CONVERGENCE RATES FOR ILL-POSED INVERSE PROBLEMS WITH AN UNKNOWN OPERATOR
Image deblurring with Poisson data: from cells to galaxies
On inverse problems with unknown operators
Bayesian inverse problems with unknown operators
On Difference-Based Variance Estimation in Nonparametric Regression When the Covariate is High Dimensional
Efficient computation of lead field bases and influence matrix for the FEM-based EEG and MEG inverse problem
Adaptive Gaussian Inverse Regression with Partially Unknown Operator
Deep Neural Network Approximation Theory
Optimal Approximation with Sparsely Connected Deep Neural Networks
Rate optimal estimation of quadratic functionals in inverse problems with partially unknown operator and application to testing problems
Solving inverse problems using data-driven models
Adaptive estimation for inverse problems with noisy operators
Approximation by superpositions of a sigmoidal function