Preconditioned iterative methods for solving weighted linear least squares problems

A class of preconditioned iterative methods, i.e., preconditioned generalized accelerated overrelaxation （GAOR） methods, is proposed to solve linear systems based on a class of weighted linear least squares problems. The convergence and comparison results are obtained. The comparison results show that the convergence rate of the preconditioned iterative methods is better than that of the original methods. Furthermore, the effectiveness of the proposed methods is shown in the numerical experiment.

An iterative algorithm for solving ill-conditioned linear least squares problems

Linear Least Squares（LLS） problems are particularly difficult to solve because they are frequently ill-conditioned, and involve large quantities of data. Ill-conditioned LLS problems are commonly seen in mathematics and geosciences, where regularization algorithms are employed to seek optimal solutions. For many problems, even with the use of regularization algorithms it may be impossible to obtain an accurate solution. Riley and Golub suggested an iterative scheme for solving LLS problems. For the early iteration algorithm, it is difficult to improve the well-conditioned perturbed matrix and accelerate the convergence at the same time. Aiming at this problem, self-adaptive iteration algorithm（SAIA） is proposed in this paper for solving severe ill-conditioned LLS problems. The algorithm is different from other popular algorithms proposed in recent references. It avoids matrix inverse by using Cholesky decomposition, and tunes the perturbation parameter according to the rate of residual error decline in the iterative process. Example shows that the algorithm can greatly reduce iteration times, accelerate the convergence,and also greatly enhance the computation accuracy.

Alternate Broyden's Method for Solving Linear Least Squares Problem with Multiple Right-Hand Sides

In this paper, we extend the alternate Broyden's method to the multiple version fbi solving lincar leastsquarc systems with multiple right-hand sides. We show that the method possesses property of a finite tcrmination.Some numerical cxperiments are gi von to inustrate the effectiveness of the method.

A COLUMN RECURRENCE ALGORITHM FOR SOLVING LINEAR LEAST SQUARES PROBLEM

A new column recurrence algorithm based on the classical Greville method and modified Huang update is proposed for computing generalized inverse matrix and least squares solution. The numerical results have shown the high efficiency and stability of the algorithm.

CONDITION NUMBER FOR WEIGHTED LINEAR LEAST SQUARES PROBLEM

In this paper, we investigate the condition numbers for the generalized matrix inversion and the rank deficient linear least squares problem： minx ｜｜Ax- b｜｜2, where A is an m-by-n （m ≥ n） rank deficient matrix. We first derive an explicit expression for the condition number in the weighted Frobenius norm ｜｜ [AT,βb] ｜｜F of the data A and b, where T is a positive diagonal matrix and β is a positive scalar. We then discuss the sensitivity of the standard 2-norm condition numbers for the generalized matrix inversion and rank deficient least squares and establish relations between the condition numbers and their condition numbers called level-2 condition numbers.

Decomposing InSAR LOS displacement into co-seismic dislocation with a linear in-terpolation model: A case study of the Kunlun Mountain M_s=8.1 earthquake

It has always been a difficult problem to extract horizontal and vertical displacement components from the InSAR LOS （Line of Sight） displacement since the advent of monitoring ground surface deformation with InSAR technique. Having tried to fit the firsthand field investigation data with a least squares model and obtained a preliminary result, this paper, based on the previous field data and the InSAR data, presents a linear cubic interpolation model which well fits the feature of earthquake fracture zone. This model inherits the precision of investigation data; moreover make use of some advantages of the InSAR technique, such as quasi-real time observation, continuous recording and all-weather measurement. Accordingly, by means of the model this paper presents a method to decompose the InSAR slant range co-seismic displacement （i.e. LOS change） into horizontal and vertical displacement components. Approaching the real motion step by step, finally a serial of curves representing the co-seismic horizontal and vertical displacement component along the main earthquake fracture zone are approximately obtained.

Greedy Randomized Gauss-Seidel Method with Oblique Direction

For the linear least squares problem with coefficient matrix columns being highly correlated, we develop a greedy randomized Gauss-Seidel method with oblique direction. Then the corresponding convergence result is deduced. Numerical examples demonstrate that our proposed method is superior to the greedy randomized Gauss-Seidel method and the randomized Gauss-Seidel method with oblique direction.

A SUCCESSIVE LEAST SQUARES METHOD FOR STRUCTURED TOTAL LEAST SQUARES

A new method for Total Least Squares (TLS) problems is presented. It differs from previous approaches and is based on the solution of successive Least Squares problems. The method is quite suitable for Structured TLS (STLS) problems. We study mostly the case of Toeplitz matrices in this paper. The numerical tests illustrate that the method converges to the solution fast for Toeplitz STLS problems. Since the method is designed for general TLS problems, other structured problems can be treated similarly.

Parameter estimation in exponential models by linear and nonlinear fitting methods

Estimation of unknown parameters in exponential models by linear and nonlinear fitting methods is discussed. Based on the extreme value theorem and Taylor series expansion, it is proved theoretically that the parameters estimated by the linear fitting method alone cannot minimize the sum of the squared residual errors in the measurement data when measurement noise is involved in the data. Numerical simulation is performed to compare the performance of the linear and nonlinear fitting methods. Simulation results show that the linear method can obtain only a suboptimal estimate of the unknown parameters and that the nonlinear method gives more accurate results. Application of the fitting methods is demonstrated where the water spectral attenuation coefficient is estimated from underwater images and imaging distances, which supports the improvement in the accuracy of parameter estimation by the nonlinear fitting method.