THE CONVERGENCE OF BROYDEN ALGORITHMS FOR LC GRADIENT FUNCTION

被引:0
|
作者
濮定国
机构
关键词
Variable metric algorithms; convex; convergence; convergence rate;
D O I
暂无
中图分类号
O241 [数值分析];
学科分类号
070102 ;
摘要
In this paper, we discuss the convergence of Broyden algorithms for the functions which are non-twice differentiable, but have LC gradient. We prove that the rate of convergence of the algorithms is linear for uniformly convex functions. We also demonstrate that under some mild conditions the algorithms are superlinsarly convergent.
引用
收藏
页码:313 / 319
页数:7
相关论文
共 50 条
  • [1] The convergence of broyden algorithms for LC gradient function
    PU Dingguo
    Acta Mathematicae Applicatae Sinica, 2000, 16 (3) : 313 - 319
  • [2] The Convergence of Broyden Algorithms Without Convexity
    Pu, Dingguo
    Liu, Ailan
    2013 SIXTH INTERNATIONAL CONFERENCE ON BUSINESS INTELLIGENCE AND FINANCIAL ENGINEERING (BIFE), 2014, : 623 - 627
  • [3] Convergence analysis of Broyden methods for LC1 constrained optimization problems
    Chen, Z.
    Jianghan Shiyou Xueyuan Xuebao/Journal of Jianghan Petroleum Institute, 2001, 23 (01): : 79 - 80
  • [4] Convergence of exponentiated gradient algorithms
    Hill, SI
    Williamson, RC
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2001, 49 (06) : 1208 - 1215
  • [5] ON THE CONVERGENCE OF CONJUGATE-GRADIENT ALGORITHMS
    PYTLAK, R
    IMA JOURNAL OF NUMERICAL ANALYSIS, 1994, 14 (03) : 443 - 460
  • [6] On the convergence of parallel Broyden method
    Zhou, Wugan
    SMART MATERIALS AND INTELLIGENT SYSTEMS, PTS 1 AND 2, 2011, 143-144 : 1148 - 1153
  • [7] A CLASS OF MODIFIED BROYDEN ALGORITHMS
    Pu Ding-guo(Department of Mathematics
    Journal of Computational Mathematics, 1994, (04) : 366 - 379
  • [8] Convergence analysis of gradient descent stochastic algorithms
    Shapiro, A
    Wardi, Y
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1996, 91 (02) : 439 - 454
  • [10] New convergence aspects of stochastic gradient algorithms
    Nguyen, Lam M.
    Nguyen, Phuong Ha
    Richtárik, Peter
    Scheinberg, Katya
    Takáč, Martin
    van Dijk, Marten
    Journal of Machine Learning Research, 2019, 20