Iterative Regularization via Dual Diagonal Descent
Author(s)Garrigos, Guillaume; Rosasco, Lorenzo; Villa, Silvia
MetadataShow full item record
In the context of linear inverse problems, we propose and study a general iterative regularization method allowing to consider large classes of data-fit terms and regularizers. The algorithm we propose is based on a primal-dual diagonal descent method. Our analysis establishes convergence as well as stability results. Theoretical findings are complemented with numerical experiments showing state-of-the-art performances.
DepartmentMcGovern Institute for Brain Research at MIT
Journal of Mathematical Imaging and Vision
Garrigos, Guillaume, et al. “Iterative Regularization via Dual Diagonal Descent.” Journal of Mathematical Imaging and Vision, vol. 60, no. 2, Feb. 2018, pp. 189–215.
Author's final manuscript