论文信息 - Linear M-estimation with bounded variables

Linear M-estimation with bounded variables

A subproblem in the trust region algorithm for non-linear M-estimation by Ekblom and Madsen is to find the restricted step. It is found by calculating the M-estimator of the linearized model, subject to anL2-norm bound on the variables. In this paper it is shown that this subproblem can be solved by applying Hebden-iterations to the minimizer of the Lagrangian function. The new method is compared with an Augmented Lagrange implementation.

O. Edlund | Ove Edlund

[1] Roger Fletcher,et al. Practical methods of optimization; (2nd ed.) , 1987 .

[2] H. B. Nielsen,et al. Finite alogorithms for robust linear regression , 1990 .

[3] Kaj Madsen,et al. Algorithms for non-linear huber estimation , 1989 .

[4] Jorge J. Moré,et al. The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[5] Kaj Madsen,et al. Algorithms for non-linear M-estimation , 1997 .