IDEAS home Printed from https://ideas.repec.org/a/wsi/apjorx/v40y2023i05ns0217595923400134.html
   My bibliography  Save this article

A Multi-Start Gradient Combination Method for High-Performance Global Search

Author

Listed:
  • Ruikang Ma

    (University of Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology of the Chinese Academy of Science, Shenzhen, Guangdong, P. R. China)

  • Pan Li

    (Southeast University Nanjing, Jiangsu, P. R. China)

  • Xinru Guo

    (University of Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology of the Chinese Academy of Science, Shenzhen, Guangdong, P. R. China)

  • Hao Zhang

    (Guangzhou C.H Control Technology, GuangZhou, Guangdong, P. R. China)

  • Qiang Zhang

    (Guangzhou C.H Control Technology, GuangZhou, Guangdong, P. R. China)

  • Li Ning

    (Shenzhen Institute for Advanced Study, UESTC, Shenzhen, Guangdong, P. R. China)

Abstract

The gradient descent is one of the most common methods to modify the gradient parameters of the neural network, however, it may fall into the local optimum in the training process. As we all know, genetic algorithm can find the global optimal solution through global search, but it may not be efficient, always takes a lot of running time. These two methods are complementary in the running time and the cost, which inspired us to consider the combination of gradient descent and genetic algorithm. In this paper, a multi-start combinatorial optimization method based on the genetic algorithm and the gradient descent is proposed. First, the initial point is selected through the genetic algorithm. Then the combination of multi-start and gradient descent is used, which can quickly achieve the global search and improve the performance with relatively less running time and cost. Compared with the traditional genetic algorithm and gradient descent method, this proposed algorithm has a better performance in computing the global optimum efficiently.

Suggested Citation

  • Ruikang Ma & Pan Li & Xinru Guo & Hao Zhang & Qiang Zhang & Li Ning, 2023. "A Multi-Start Gradient Combination Method for High-Performance Global Search," Asia-Pacific Journal of Operational Research (APJOR), World Scientific Publishing Co. Pte. Ltd., vol. 40(05), pages 1-13, October.
    • Handle: RePEc:wsi:apjorx:v:40:y:2023:i:05:n:s0217595923400134
    DOI: 10.1142/S0217595923400134
    as

    Download full text from publisher

    File URL: http://www.worldscientific.com/doi/abs/10.1142/S0217595923400134
    Download Restriction: Access to full text is restricted to subscribers
    File URL: https://libkey.io/10.1142/S0217595923400134?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:wsi:apjorx:v:40:y:2023:i:05:n:s0217595923400134. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Tai Tone Lim (email available below). General contact details of provider: http://www.worldscinet.com/apjor/apjor.shtml .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.