Global optimization of non-convex piecewise linear regression splines

被引：8
|
作者：
Martinez, Nadia [1 ]
Anahideh, Hadis [2 ]
Rosenberger, Jay M. [2 ]
Martinez, Diana [3 ]
Chen, Victoria C. P. [2 ]
Wang, Bo Ping [4 ]
机构：
[1] Amer Airlines Inc, 4333 Amon Carter Blvd,HDQ1 MD 5358, Ft Worth, TX 76155 USA
[2] Univ Texas Arlington, Dept Ind & Mfg Syst Engn, Arlington, TX 76019 USA
[3] TMAC, 202 E Border St,Ste 323, Arlington, TX 76010 USA
[4] Univ Texas Arlington, Dept Mech & Aerosp Engn, Arlington, TX 76019 USA
来源：
JOURNAL OF GLOBAL OPTIMIZATION | 2017年 / 68卷 / 03期
基金：
美国国家科学基金会;
关键词：
Global optimization; Branch and bound; Surrogate methods; Multivariate adaptive regression splines; Crashworthiness; Genetic algorithms; DESIGN; ALGORITHM; CRASHWORTHINESS;
D O I：
10.1007/s10898-016-0494-5
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：
Multivariate adaptive regression spline (MARS) is a statistical modeling method used to represent a complex system. More recently, a version of MARS was modified to be piecewise linear. This paper presents a mixed integer linear program, called MARSOPT, that optimizes a non-convex piecewise linear MARS model subject to constraints that include both linear regression models and piecewise linear MARS models. MARSOPT is customized for an automotive crash safety system design problem for a major US automaker and solved using branch and bound. The solutions from MARSOPT are compared with those from customized genetic algorithms.
引用
收藏
页码：563 / 586
页数：24
相关论文
共 50 条
  • [1] Global optimization of non-convex piecewise linear regression splines
    Nadia Martinez
    Hadis Anahideh
    Jay M. Rosenberger
    Diana Martinez
    Victoria C. P. Chen
    Bo Ping Wang
    Journal of Global Optimization, 2017, 68 : 563 - 586
  • [2] Global optimization on non-convex two-way interaction truncated linear multivariate adaptive regression splines using mixed integer quadratic programming
    Ju, Xinglong
    Rosenberger, Jay M.
    Chen, Victoria C. P.
    Liu, Feng
    INFORMATION SCIENCES, 2022, 597 : 38 - 52
  • [3] Global optimization on non-convex two-way interaction truncated linear multivariate adaptive regression splines using mixed integer quadratic programming
    Ju, Xinglong
    Rosenberger, Jay M.
    Chen, Victoria C.P.
    Liu, Feng
    Information Sciences, 2022, 597 : 38 - 52
  • [4] A DIFFERENCE OF CONVEX OPTIMIZATION ALGORITHM FOR PIECEWISE LINEAR REGRESSION
    Bagirov, Adil
    Taheri, Sona
    Asadi, Soodabeh
    JOURNAL OF INDUSTRIAL AND MANAGEMENT OPTIMIZATION, 2019, 15 (02) : 909 - 932
  • [5] Distributed non-convex regularization for generalized linear regression
    Sun, Xiaofei
    Zhang, Jingyu
    Liu, Zhongmo
    Polat, Kemal
    Gai, Yujie
    Gao, Wenliang
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 252
  • [6] Non-convex global optimization with Gurman perturbation
    Chen, S. (daisyshuoshuo@sina.com), 1600, Science Press (41):
  • [7] Global Non-convex Optimization with Discretized Diffusions
    Erdogdu, Murat A.
    Mackey, Lester
    Shamir, Ohad
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [8] Global Optimization Approach to Non-convex Problems
    LU Zi-fang
    The Journal of China Universities of Posts and Telecommunications, 2004, (03) : 108 - 111
  • [9] A Global Optimization Approach to Non-Convex Problems
    Lu, Z. F.
    Lan, Y.
    PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INDUSTRIAL ENGINEERING (AIIE 2015), 2015, 123 : 449 - 452
  • [10] A new accelerating method for global non-convex quadratic optimization with non-convex quadratic constraints
    Wu, Huizhuo
    Zhang, KeCun
    APPLIED MATHEMATICS AND COMPUTATION, 2008, 197 (02) : 810 - 818
12345