Risk estimators for choosing regularization parameters in ill-posed problems - properties and limitations
Inverse Problems and Imaging, pp. 1121-1155, 2018.
This paper discusses the properties of certain risk estimators that recently regained popularity for choosing regularization parameters in ill-posed problems, in particular for sparsity regularization. They apply Steinu0027s unbiased risk estimator (SURE) to estimate the risk in either the space of the unknown variables or in the data spa...More
Full Text (Upload PDF)
PPT (Upload PPT)