Convex regularization in statistical inverse learning problems Article Swipe

PDF

Related Concepts

Regularization (linguistics) Tikhonov regularization Bregman divergence Inverse problem Mathematics Convex function Applied mathematics Regular polygon Operator (biology) Convex optimization Mathematical optimization Mathematical analysis Computer science Artificial intelligence Transcription factor Repressor Biochemistry Geometry Gene Chemistry

Tatiana A. Bubba , Martin Burger , Tapio Helin , Luca Ratti ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.3934/ipi.2023013 · OA: W3130603238

We consider a statistical inverse learning problem, where the task is to estimate a function f based on noisy point evaluations of Af, where A is a linear operator. The function Af is evaluated at i.i.d. random design points u(n), n = 1, ..., N generated by an unknown general probability distribution. We consider Tikhonov regularization with general convex and p-homogeneous penalty functionals and derive concentration rates of the regularized solution to the ground truth measured in the symmetric Bregman distance induced by the penalty functional. We derive concrete rates for Besov norm penalties and numerically demonstrate the correspondence with the observed rates in the context of X-ray tomography.