NETT: Solving Inverse Problems with Deep Neural Networks

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, theoretical results for deep learning in inverse problems are missing so far. In this paper, we establish such a convergence analysis for the proposed NETT (Network Tikhonov) approach to inverse problems. NETT considers regularized solutions having small value of a regularizer defined by a trained neural network. Opposed to existing deep learning approaches, our regularization scheme enforces data consistency also for the actual unknown to be recovered. This is beneficial in case the unknown to be recovered is not sufficiently similar to available training data. We present a complete convergence analysis for NETT, where we derive well-posedness results and quantitative error estimates, and propose a possible strategy for training the regularizer. Numerical results are presented for a tomographic sparse data problem using the l-norm of auto-encoder as trained regularizer, which demonstrate good performance of NETT even for unknowns of different type from the training data.