On learning the optimal regularization parameter in inverse problems
Open Access
- 4 November 2024
- journal article
- research article
- Published by IOP Publishing in Inverse Problems
- Vol. 40 (12) , 125004
Abstract
Selecting the best regularization parameter in inverse problems is a classical and yet challenging problem. Recently, data-driven approaches based on supervised learning 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 based on supervised learning to inverse problems.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- On regularized polynomial functional regressionJournal of Complexity, 2024
- Modern regularization methods for inverse problemsActa Numerica, 2018
- Phase recovery, MaxCut and complex semidefinite programmingMathematical Programming, 2013
- Comparingparameter choice methods for regularization of ill-posed problemsMathematics and Computers in Simulation, 2011
- Logarithmic convergence rates for the identification of a nonlinear Robin coefficientJournal of Mathematical Analysis and Applications, 2009
- Error estimation for Bregman iterations and inverse scale space methods in image restorationComputing, 2007
- On regularization algorithms in learning theoryJournal of Complexity, 2007
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraintCommunications on Pure and Applied Mathematics, 2004
- Image recovery via total variation minimization and related problemsNumerische Mathematik, 1997
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992