Estimating the regularization parameter efficiently
We consider linear inverse problems with a two norm regularization, called Tikhonov regularization. When using regularization to solve an inverse problem, a regularization parameter is introduced. The regularization parameter heavily controls the quality of the regularized solution. We show various methods to estimate the regularization parameter known from literature that arise in various applications. Furthermore, we will describe how to efficiently evaluate them. We show results on a 2D seismic travel time tomography problem.
|EAGE Conference and Exhibition|
Luiken, N, & van Leeuwen, T. (2018). Estimating the regularization parameter efficiently. In 80th EAGE Conference and Exhibition 2018 (pp. 1–5). doi:10.3997/2214-4609.201801348