Addendum on data driven regularization by projection
By: Martin Hanke, Otmar Scherzer
Potential Business Impact:
Teaches computers to fix blurry pictures from examples.
We study the stability of regularization by projection for solving linear inverse problems if the forward operator is given indirectly but specified via some input-output training pairs. We extend the approach in "Data driven regularization by projection" (Aspri, Korolev, and Scherzer; Inverse Problems; 36 (2020), 125009) to data pairs, which are noisy and, possibly, linearly dependent.
Similar Papers
Introduction to Regularization and Learning Methods for Inverse Problems
Numerical Analysis
Teaches computers to solve tricky puzzles from incomplete clues.
From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent
Image and Video Processing
Fixes broken pictures using smart math.
Stochastic Orthogonal Regularization for deep projective priors
Image and Video Processing
Makes computers fix blurry pictures faster.