31 citations · 43 across the 3 of their papers we have counts for
3 papers
math.OC2021
How many samples are needed to reliably approximate the best linear estimator for a linear inverse problem?
Gernot Holler
The linear minimum mean squared error (LMMSE) estimator is the best linear estimator for a Bayesian linear inverse problem with respect to the mean squared error. It arises as the…
math.OC2020★ 12 cited
Learning nonlocal regularization operators
Gernot Holler, Karl Kunisch
A learning approach for determining which operator from a class of nonlocal operators is optimal for the regularization of an inverse problem is investigated. The considered class…
math.OC2018★ 31 cited
A Bilevel Approach for Parameter Learning in Inverse Problems
Gernot Holler, Karl Kunisch, Richard C. Barnard
A learning approach to selecting regularization parameters in multi-penalty Tikhonov regularization is investigated. It leads to a bilevel optimization problem, where the lower lev…