On Learning the Optimal Regularization Parameter in Inverse Problems

Abstract

Selecting the best regularization parameter in inverse problems is a classical and yet challenging problem. Recently, data-driven approaches have become popular to tackle this challenge. These approaches are appealing since they do require less a priori knowledge, but their theoretical analysis is limited. In this paper, we propose and study a statistical machine learning approach, based on empirical risk minimization. Our main contribution is a theoretical analysis, showing that, provided with enough data, this approach can reach sharp rates while being essentially adaptive to the noise and smoothness of the problem. Numerical simulations corroborate and illustrate the theoretical findings. Our results are a step towards grounding theoretically data-driven approaches to inverse problems.

References in corpus (8)

• High-dimensional graphs and variable selection with the Lasso
• Sparse Regularization with $l^q$ Penalty Term
• Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
• Regularization independent of the noise level: an analysis of quasi-optimality
• Data driven regularization by projection
• Regularization of Inverse Problems
• On regularized polynomial functional regression
• Nonlinear functional regression by functional deep neural network with kernel embedding