25 citations · 50 across the 4 of their papers we have counts for
4 papers
Why the noise model matters: A performance gap in learned regularization
Sebastian Banert, Christoph Brauer, Dirk Lorenz +1
This article addresses the challenge of learning effective regularizers for linear inverse problems. We analyze and compare several types of learned variational regularization agai…
Accelerated Forward-Backward Optimization using Deep Learning
Sebastian Banert, Jevgenija Rudzusika, Ozan Öktem +1
We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, bu…
A data-driven iteratively regularized Landweber iteration
Andrea Aspri, Sebastian Banert, Ozan Öktem +1
We derive and analyse a new variant of the iteratively regularized Landweber iteration, for solving linear and nonlinear ill-posed inverse problems. The method takes into account t…
Data-driven nonsmooth optimization
Sebastian Banert, Axel Ringh, Jonas Adler +2
In this work, we consider methods for solving large-scale optimization problems with a possibly nonsmooth objective function. The key idea is to first specify a class of optimizati…