A bilevel training scheme is used to introduce a novel class of regularizers, providing a unified approach to standard regularizers and . Optimal parameters and regularizers are identified, and the existence of a solution for any given set of training imaging data is proved by -convergence under a conditional uniform bound on the trace constant of the operators and a finite-null-space condition. Some first examples and numerical results are given.
Keywords:
© The Author(s) 2023.