IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i19p3556-d929180.html
   My bibliography  Save this article

Accelerating Extreme Search of Multidimensional Functions Based on Natural Gradient Descent with Dirichlet Distributions

Author

Listed:
  • Ruslan Abdulkadirov

    (North-Caucasus Center for Mathematical Research, North-Caucasus Federal University, 355009 Stavropol, Russia)

  • Pavel Lyakhov

    (North-Caucasus Center for Mathematical Research, North-Caucasus Federal University, 355009 Stavropol, Russia
    Department of Mathematical Modeling, North-Caucasus Federal University, 355009 Stavropol, Russia)

  • Nikolay Nagornov

    (Department of Mathematical Modeling, North-Caucasus Federal University, 355009 Stavropol, Russia)

Abstract

The high accuracy attainment, using less complex architectures of neural networks, remains one of the most important problems in machine learning. In many studies, increasing the quality of recognition and prediction is obtained by extending neural networks with usual or special neurons, which significantly increases the time of training. However, engaging an optimization algorithm, which gives us a value of the loss function in the neighborhood of global minimum, can reduce the number of layers and epochs. In this work, we explore the extreme searching of multidimensional functions by proposed natural gradient descent based on Dirichlet and generalized Dirichlet distributions. The natural gradient is based on describing a multidimensional surface with probability distributions, which allows us to reduce the change in the accuracy of gradient and step size. The proposed algorithm is equipped with step-size adaptation, which allows it to obtain higher accuracy, taking a small number of iterations in the process of minimization, compared with the usual gradient descent and adaptive moment estimate. We provide experiments on test functions in four- and three-dimensional spaces, where natural gradient descent proves its ability to converge in the neighborhood of global minimum. Such an approach can find its application in minimizing the loss function in various types of neural networks, such as convolution, recurrent, spiking and quantum networks.

Suggested Citation

  • Ruslan Abdulkadirov & Pavel Lyakhov & Nikolay Nagornov, 2022. "Accelerating Extreme Search of Multidimensional Functions Based on Natural Gradient Descent with Dirichlet Distributions," Mathematics, MDPI, vol. 10(19), pages 1-13, September.
  • Handle: RePEc:gam:jmathe:v:10:y:2022:i:19:p:3556-:d:929180
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/19/3556/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/10/19/3556/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gómez, Yolanda M. & Bolfarine, Heleno & Gómez, Héctor W., 2019. "Gumbel distribution with heavy tails and applications to environmental data," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 157(C), pages 115-129.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Ruslan Abdulkadirov & Pavel Lyakhov & Nikolay Nagornov, 2023. "Survey of Optimization Algorithms in Modern Neural Networks," Mathematics, MDPI, vol. 11(11), pages 1-37, May.
    2. Abdulkadirov, R. & Lyakhov, P. & Bergerman, M. & Reznikov, D., 2024. "Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum," Chaos, Solitons & Fractals, Elsevier, vol. 179(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Neveka M. Olmos & Emilio Gómez-Déniz & Osvaldo Venegas, 2022. "The Heavy-Tailed Gleser Model: Properties, Estimation, and Applications," Mathematics, MDPI, vol. 10(23), pages 1-16, December.
    2. Ziad M. Ali & Shady H. E. Abdel Aleem & Ahmed I. Omar & Bahaa Saad Mahmoud, 2022. "Economical-Environmental-Technical Operation of Power Networks with High Penetration of Renewable Energy Systems Using Multi-Objective Coronavirus Herd Immunity Algorithm," Mathematics, MDPI, vol. 10(7), pages 1-43, April.
    3. Talha Arslan, 2021. "An α -Monotone Generalized Log-Moyal Distribution with Applications to Environmental Data," Mathematics, MDPI, vol. 9(12), pages 1-18, June.
    4. Ahmed I. Omar & Ziad M. Ali & Mostafa Al-Gabalawy & Shady H. E. Abdel Aleem & Mujahed Al-Dhaifallah, 2020. "Multi-Objective Environmental Economic Dispatch of an Electricity System Considering Integrated Natural Gas Units and Variable Renewable Energy Sources," Mathematics, MDPI, vol. 8(7), pages 1-37, July.
    5. Juan M. Astorga & Jimmy Reyes & Karol I. Santoro & Osvaldo Venegas & Héctor W. Gómez, 2020. "A Reliability Model Based on the Incomplete Generalized Integro-Exponential Function," Mathematics, MDPI, vol. 8(9), pages 1-12, September.
    6. Nagode, Marko & Oman, Simon & Klemenc, Jernej & Panić, Branislav, 2023. "Gumbel mixture modelling for multiple failure data," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    7. Francisco A. Segovia & Yolanda M. Gómez & Osvaldo Venegas & Héctor W. Gómez, 2020. "A Power Maxwell Distribution with Heavy Tails and Applications," Mathematics, MDPI, vol. 8(7), pages 1-20, July.

    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:gam:jmathe:v:10:y:2022:i:19:p:3556-:d:929180. 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.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.