Residual Periodograms for Choosing Regularization Parameters for Ill-Posed Problems
Bert W. Rust, Dianne M. O'Leary
Consider an ill-posed problem transformed if necessary so that the errors in the data are independent, identically normally distributed with mean zero and variance 1. We evaluate a method proposed by Rust for choosing the regularization parameter that makes the residuals as close as possible to white noise, using a test based on the cumulative periodogram. We compare this method with standard techniques such as the discrepancy principle, the L-curve, and generalized cross validation, showing that it performs better.
and O'Leary, D.
Residual Periodograms for Choosing Regularization Parameters for Ill-Posed Problems, Inverse Problems, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=51212
(Accessed December 7, 2023)