Regularization parameter estimation for large-scale Tikhonov regularization using a priori information

• Authors: Rosemary A. Renaut;Iveta Hntynková;Jodi Mead
• Venue: Computational Statistics & Data Analysis
• Year: 2010

Solutions of numerically ill-posed least squares problems Ax~b for A@?R^m^x^n by Tikhonov regularization are considered. For D@?R^p^x^n, the Tikhonov regularized least squares functional is given by J(@s)=@?Ax-b@?"W^2+1/@s^2@?D(x-x"0)@?"2^2 where matrix W is a weighting matrix and x"0 is given. Given a priori estimates on the covariance structure of errors in the measurement data b, the weighting matrix may be taken as W=W"b which is the inverse covariance matrix of the mean 0 normally distributed measurement errors e in b. If in addition x"0 is an estimate of the mean value of x, and @s is a suitable statistically-chosen value, J evaluated at its minimizer x(@s) approximately follows a @g^2 distribution with m@?=m+p-n degrees of freedom. Using the generalized singular value decomposition of the matrix pair [W"b^1^/^2AD], @s can then be found such that the resulting J follows this @g^2 distribution. But the use of an algorithm which explicitly relies on the direct solution of the problem obtained using the generalized singular value decomposition is not practical for large-scale problems. Instead an approach using the Golub-Kahan iterative bidiagonalization of the regularized problem is presented. The original algorithm is extended for cases in which x"0 is not available, but instead a set of measurement data provides an estimate of the mean value of b. The sensitivity of the Newton algorithm to the number of steps used in the Golub-Kahan iterative bidiagonalization, and the relation between the size of the projected subproblem and @s are discussed. Experiments presented contrast the efficiency and robustness with other standard methods for finding the regularization parameter for a set of test problems and for the restoration of a relatively large real seismic signal. An application for image deblurring also validates the approach for large-scale problems. It is concluded that the presented approach is robust for both small and large-scale discretely ill-posed least squares problems.