A note on inexact gradient and Hessian conditions for cubic regularized Newton's method

被引:5
|
作者
Wang, Zhe [1 ]
Zhou, Yi [2 ]
Liang, Yingbin [1 ]
Lan, Guanghui [3 ]
机构
[1] Ohio State Univ, Dept Elect & Comp Engn, Columbus, OH 43210 USA
[2] Duke Univ, Dept Elect & Comp Engn, Durham, NC 27708 USA
[3] Georgia Inst Technol, Dept Ind & Syst Engn, Atlanta, GA 30332 USA
基金
美国国家科学基金会;
关键词
Nonconvex; Second-order methods; Second-order stationary points;
D O I
10.1016/j.orl.2019.01.009
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
The inexact cubic-regularized Newton's method (CR) proposed by Cartis, Gould and Toint achieves the same convergence rate as exact CR proposed by Nesterov and Polyak, but the inexact condition is not implementable due to its dependence on a future variable. This note establishes the same convergence rate under a similar but implementable inexact condition, which depends on only current variables. Our proof bounds the function-value decrease over total iterations rather than each iteration in the previous studies. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页码:146 / 149
页数:4
相关论文
共 50 条
  • [31] A truncated conjugate gradient method with an inexact Gauss-Newton technique for solving nonlinear systems
    Yong Zhang
    Detong Zhu
    Journal of Applied Mathematics and Computing, 2012, 38 (1-2) : 551 - 564
  • [32] A truncated conjugate gradient method with an inexact Gauss-Newton technique for solving nonlinear systems
    Zhang, Yong
    Zhu, Detong
    JOURNAL OF APPLIED MATHEMATICS AND COMPUTING, 2012, 38 (1-2) : 551 - 564
  • [33] Local Convergence of Inexact Newton-Like Method under Weak Lipschitz Conditions
    Ioannis K. Argyros
    Yeol Je Cho
    Santhosh George
    Yibin Xiao
    Acta Mathematica Scientia, 2020, 40 : 199 - 210
  • [34] Local Convergence of Inexact Newton-Like Method under Weak Lipschitz Conditions
    Argyros, Ioannis K.
    Cho, Yeol Je
    George, Santhosh
    Xiao, Yibin
    ACTA MATHEMATICA SCIENTIA, 2020, 40 (01) : 199 - 210
  • [35] LOCAL CONVERGENCE OF INEXACT NEWTON-LIKE METHOD UNDER WEAK LIPSCHITZ CONDITIONS
    Ioannis K.ARGYROS
    Yeol Je CHO
    Santhosh GEORGE
    肖义彬
    ActaMathematicaScientia, 2020, 40 (01) : 199 - 210
  • [36] Inexact Newton’s method with inner implicit preconditioning for algebraic Riccati equations
    Jean-Paul Chehab
    Marcos Raydan
    Computational and Applied Mathematics, 2017, 36 : 955 - 969
  • [37] Newton’s method with feasible inexact projections for solving constrained generalized equations
    Fabiana R. de Oliveira
    Orizon P. Ferreira
    Gilson N. Silva
    Computational Optimization and Applications, 2019, 72 : 159 - 177
  • [38] Newton's method with feasible inexact projections for solving constrained generalized equations
    de Oliveira, Fabiana R.
    Ferreira, Orizon P.
    Silva, Gilson N.
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2019, 72 (01) : 159 - 177
  • [39] Inexact Newton's method with inner implicit preconditioning for algebraic Riccati equations
    Chehab, Jean-Paul
    Raydan, Marcos
    COMPUTATIONAL & APPLIED MATHEMATICS, 2017, 36 (02): : 955 - 969
  • [40] The Hessian Riemannian flow and Newton's method for effective Hamiltonians and Mather measures
    Gomes, Diogo A.
    Yang, Xianjin
    ESAIM-MATHEMATICAL MODELLING AND NUMERICAL ANALYSIS-MODELISATION MATHEMATIQUE ET ANALYSE NUMERIQUE, 2020, 54 (06): : 1883 - 1915