Application of Stochastic Gradient Descent Technique for Method of Moments

被引：0
|
作者：
Guo, Liangshuai [1 ,2 ]
Li, Maokun [1 ]
Xu, Shenheng [1 ]
Yang, Fan [1 ]
机构：
[1] Tsinghua Univ, Dept Elect Engn, Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China
[2] Sci & Technol Electromagnet Scattering Lab, Shanghai, Peoples R China
来源：
PROCEEDINGS OF THE 2020 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL ELECTROMAGNETICS (ICCEM 2020) | 2020年
基金：
美国国家科学基金会;
关键词：
Method of moments (MoM); Stochastic Gradient Descent (SGD); Parallelization; Matrix equation solver; ALGORITHM;
D O I：
10.1109/iccem47450.2020.9219400
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
This paper studies the feasibility of solving matrix equations in the method of moment (MoM) based on the stochastic gradient descent (SGD) technique (SGD-MoM). We adopted the optimization techniques in machine learning to solve the matrix equations in MoM. Numerical result demonstrate the feasibility of the proposed method, and its accuracy and efficiency, compared with conventional iterative methods like conjugate gradient(CG), generalized minimal residual algorithm (GMRES), and etc.
引用
收藏
页码：97 / 98
页数：2
相关论文
共 50 条
  • [1] BACKPROPAGATION AND STOCHASTIC GRADIENT DESCENT METHOD
    AMARI, S
    [J]. NEUROCOMPUTING, 1993, 5 (4-5) : 185 - 196
  • [2] Stochastic gradient descent with variance reduction technique
    Zhang, Jinjing
    Hu, Fei
    Xu, Xiaofei
    Li, Li
    [J]. WEB INTELLIGENCE, 2018, 16 (03) : 187 - 194
  • [3] Beam cleanup technique based on stochastic parallel gradient descent wavefront control method
    Liang Yonghui
    Wang Sanhong
    Long Xuejun
    Yu Qifeng
    [J]. HIGH-POWER LASERS AND APPLICATIONS IV, 2008, 6823
  • [4] ADINE: An Adaptive Momentum Method for Stochastic Gradient Descent
    Srinivasan, Vishwak
    Sankar, Adepu Ravi
    Balasubramanian, Vineeth N.
    [J]. PROCEEDINGS OF THE ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE AND MANAGEMENT OF DATA (CODS-COMAD'18), 2018, : 249 - 256
  • [5] On the Convergence of Stochastic Compositional Gradient Descent Ascent Method
    Gao, Hongchang
    Wang, Xiaoqian
    Luo, Lei
    Shi, Xinghua
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 2389 - 2395
  • [6] AN APPLICATION OF METHOD OF MOMENTS TO STOCHASTIC EQUATIONS
    MCCOY, JJ
    [J]. QUARTERLY OF APPLIED MATHEMATICS, 1969, 26 (04) : 521 - &
  • [7] Unforgeability in Stochastic Gradient Descent
    Baluta, Teodora
    Nikolic, Ivica
    Jain, Racchit
    Aggarwal, Divesh
    Saxena, Prateek
    [J]. PROCEEDINGS OF THE 2023 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, CCS 2023, 2023, : 1138 - 1152
  • [8] Preconditioned Stochastic Gradient Descent
    Li, Xi-Lin
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (05) : 1454 - 1466
  • [9] Stochastic Reweighted Gradient Descent
    El Hanchi, Ayoub
    Stephens, David A.
    Maddison, Chris J.
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [10] Byzantine Stochastic Gradient Descent
    Alistarh, Dan
    Allen-Zhu, Zeyuan
    Li, Jerry
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
12345