Efficient determination of the hyperparameter in regularized total least squares problems

被引：10
|
作者：
Lampe, J. [1 ]
Voss, H. [1 ]
机构：
[1] Hamburg Univ Technol, Inst Numer Simulat, D-21071 Hamburg, Germany
来源：
APPLIED NUMERICAL MATHEMATICS | 2012年 / 62卷 / 09期
关键词：
Total least squares; Regularization; Ill-posedness; Nonlinear Arnoldi method; L-curve; TIKHONOV REGULARIZATION; ARNOLDI METHOD; L-CURVE; ALGORITHM;
D O I：
10.1016/j.apnum.2010.06.005
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
The total least squares (TLS) method is a successful approach for linear problems if both the system matrix and the right-hand side are contaminated by some noise. For ill-posed TLS problems regularization is necessary to stabilize the computed solution. In this paper we suggest the use of the L-curve for the determination of the regularization parameter. The focus is on efficient implementation with particular emphasis on the reuse of information gained during the convergence history. (c) 2010 IMACS. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码：1229 / 1241
页数：13
相关论文
共 50 条
  • [41] REGULARIZED CONSTRAINED TOTAL LEAST-SQUARES IMAGE-RESTORATION
    MESAROVIC, VZ
    GALATSANOS, NP
    KATSAGGELOS, AK
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1995, 4 (08) : 1096 - 1108
  • [42] PREDICTION BOUNDS FOR HIGHER ORDER TOTAL VARIATION REGULARIZED LEAST SQUARES
    Ortelli, Francesco
    van de Geer, Sara
    [J]. ANNALS OF STATISTICS, 2021, 49 (05): : 2755 - 2773
  • [43] Regularized total least squares based on quadratic eigenvalue problem solvers
    Sima, DM
    Van Huffel, S
    Golub, GH
    [J]. BIT NUMERICAL MATHEMATICS, 2004, 44 (04) : 793 - 812
  • [44] Adaptively regularized constrained total least-squares image restoration
    Chen, WF
    Chen, M
    Zhou, J
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (04) : 588 - 596
  • [45] Regularized Total Least Squares Based on Quadratic Eigenvalue Problem Solvers
    Diana M. Sima
    Sabine Van Huffel
    Gene H. Golub
    [J]. BIT Numerical Mathematics, 2004, 44 : 793 - 812
  • [46] Iterative and regularized algorithm to ill-posed total least squares
    [J]. Sun, Tong-He (suntonghe202@163.com), 2016, Central South University of Technology (26):
  • [47] Some Iterative Regularized Methods for Highly Nonlinear Least Squares Problems
    Kangro, I.
    Vaarmann, O.
    [J]. MATHEMATICAL MODELLING AND ANALYSIS, 2009, 14 (02) : 179 - 186
  • [48] Safe Subspace Screening for Nuclear Norm Regularized Least Squares Problems
    Zhou, Qiang
    Zhao, Qi
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 1103 - 1112
  • [49] A Gauss-Newton method for mixed least squares-total least squares problems
    Liu, Qiaohua
    Wang, Shan
    Wei, Yimin
    [J]. CALCOLO, 2024, 61 (01)
  • [50] Methods for large scale total least squares problems
    Björck, Å
    Heggernes, P
    Matstoms, P
    [J]. SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2000, 22 (02) : 413 - 429
12345