Regularization by early stopping for general inverse problems
schedule le mardi 20 février 2018 de 12h00 à 13h00
Organisé par : I. Castillo, A. Fischer, E. Roquain, M. Sangnier
Intervenant : Guillaume Garrigos (DMA - CNRS)
Lieu : Paris-Diderot, salle 2015
Sujet : Regularization by early stopping for general inverse problems
In the context of linear inverse problems, we propose and study a general iterative regularization method allowing to consider large classes of regularizers and data-fit terms. We focus particularly on non-smooth data-fit terms, such like a Kullback-Liebler divergence, or an L1 distance. We treat these problems by designing an algorithm, based on a primal-dual diagonal descent method, designed to solve bilevel optimization problems. The key point of our approach is that, in presence of noise, the number of iterations of our algorithm acts as a regularization parameter. In practice this means that the algorithm must be stopped after a certain number of iterations. This is what is called regularization by /early stopping/, an approach which gained in popularity in statistical learning. Our main results establishes convergence and stability of our algorithm, and are illustrated by experiments on image denoising, comparing our approach with a more classical Tikhonov regularization method.