DeepAI AI Chat
Log In Sign Up

Deep learning for inverse problems with unknown operator

by   Miguel del Álamo, et al.

We consider ill-posed inverse problems where the forward operator T is unknown, and instead we have access to training data consisting of functions f_i and their noisy images Tf_i. This is a practically relevant and challenging problem which current methods are able to solve only under strong assumptions on the training set. Here we propose a new method that requires minimal assumptions on the data, and prove reconstruction rates that depend on the number of training points and the noise level. We show that, in the regime of "many" training data, the method is minimax optimal. The proposed method employs a type of convolutional neural networks (U-nets) and empirical risk minimization in order to "fit" the unknown operator. In a nutshell, our approach is based on two ideas: the first is to relate U-nets to multiscale decompositions such as wavelets, thereby linking them to the existing theory, and the second is to use the hierarchical structure of U-nets and the low number of parameters of convolutional neural nets to prove entropy bounds that are practically useful. A significant difference with the existing works on neural networks in nonparametric statistics is that we use them to approximate operators and not functions, which we argue is mathematically more natural and technically more convenient.


page 1

page 2

page 3

page 4


Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

We study the problem of reconstructing solutions of inverse problems whe...

Model-Aware Regularization For Learning Approaches To Inverse Problems

There are various inverse problems – including reconstruction problems a...

Solving ill-posed inverse problems using iterative deep neural networks

We propose a partially learned approach for the solution of ill posed in...

Total variation multiscale estimators for linear inverse problems

Even though the statistical theory of linear inverse problems is a well-...

Deep Mesh Projectors for Inverse Problems

We develop a new learning-based approach to ill-posed inverse problems. ...

Convolutional Neural Networks Analyzed via Inverse Problem Theory and Sparse Representations

Inverse problems in imaging such as denoising, deblurring, superresoluti...