Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow

被引:8
|
作者
Indrapriyadarsini, S. [1 ]
Mahboubi, Shahrzad [2 ]
Ninomiya, Hiroshi [2 ]
Asai, Hideki [3 ]
机构
[1] Shizuoka Univ, Grad Sch Integrated Sci & Technol, Hamamatsu, Shizuoka, Japan
[2] Shonan Inst Technol, Grad Sch Elect & Informat Engn, Fujisawa, Kanagawa, Japan
[3] Shizuoka Univ, Res Inst Elect, Hamamatsu, Shizuoka, Japan
关键词
Neural networks; training algorithm; quasi-Newton method; Nesterov's accelerated gradient; Global convergence; Tensorflow; highly-nonlinear function modeling;
D O I
10.1109/ICMLA.2018.00185
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recent studies incorporate Nesterov's accelerated gradient method for the acceleration of gradient based training. The Nesterov's Accelerated Quasi-Newton (NAQ) method has shown to drastically improve the convergence speed compared to the conventional quasi-Newton method. This paper implements NAQ for non-convex optimization on Tensorflow. Two modifications have been proposed to the original NAQ algorithm to ensure global convergence and eliminate linesearch. The performance of the proposed algorithm - mNAQ is evaluated on standard non-convex function approximation benchmark problems and microwave circuit modelling problems. The results show that the improved algorithm converges better and faster compared to first order optimizers such as AdaGrad, RMSProp, Adam, and the second order methods such as the quasi-Newton method.
引用
收藏
页码:1147 / 1154
页数:8
相关论文
共 50 条
  • [1] On the Practical Robustness of the Nesterov's Accelerated Quasi-Newton Method
    Indrapriyadarsini, S.
    Ninomiya, Hiroshi
    Kamio, Takeshi
    Asai, Hideki
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 12884 - 12885
  • [2] A Stochastic Quasi-Newton Method with Nesterov's Accelerated Gradient
    Indrapriyadarsini, S.
    Mahboubi, Shahrzad
    Ninomiya, Hiroshi
    Asai, Hideki
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2019, PT I, 2020, 11906 : 743 - 760
  • [3] The regularized stochastic Nesterov?s accelerated Quasi-Newton method with applications
    Makmuang, Dawrawee
    Suppalap, Siwakon
    Wangkeeree, Rabian
    [J]. JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2023, 428
  • [4] aSNAQ: An adaptive stochastic Nesterov's accelerated quasi-Newton method for training RNNs
    Sendilkkumaar, Indrapriyadarsini
    Mahboubi, Shahrzad
    Ninomiya, Hiroshi
    Asai, Hideki
    [J]. IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2020, 11 (04): : 409 - 421
  • [5] A Nesterov's accelerated quasi-Newton method for global routing using deep reinforcement learning
    Indrapriyadarsini, S.
    Mahboubi, Shahrzad
    Ninomiya, Hiroshi
    Kamio, Takeshi
    Asai, Hideki
    [J]. IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2021, 12 (03): : 323 - 335
  • [6] Neural Network Training based on quasi-Newton Method using Nesterov's Accelerated Gradient
    Ninomiya, Hiroshi
    [J]. PROCEEDINGS OF THE 2016 IEEE REGION 10 CONFERENCE (TENCON), 2016, : 51 - 54
  • [7] A Neural Network approach to Analog Circuit Design Optimization using Nesterov's Accelerated Quasi-Newton Method
    Indrapriyadarsini, S.
    Mahboubi, Shahrzad
    Ninomiya, Hiroshi
    Kamio, Takeshi
    Asai, Hideki
    [J]. 2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
  • [8] On quasi-Newton methods with modified quasi-Newton equation
    Xiao, Wei
    Sun, Fengjian
    [J]. PROCEEDINGS OF 2008 INTERNATIONAL PRE-OLYMPIC CONGRESS ON COMPUTER SCIENCE, VOL II: INFORMATION SCIENCE AND ENGINEERING, 2008, : 359 - 363
  • [9] A quasi-Newton modified LP-Newton method
    de los Angeles Martinez, Maria
    Fernandez, Damian
    [J]. OPTIMIZATION METHODS & SOFTWARE, 2019, 34 (03): : 634 - 649
  • [10] A modified quasi-Newton method for nonlinear equations
    Fang, Xiaowei
    Ni, Qin
    Zeng, Meilan
    [J]. JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2018, 328 : 44 - 58