IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v12y2024i15p2393-d1447312.html
   My bibliography  Save this article

A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints

Author

Listed:
  • Rulei Qi

    (School of Mathematics and Statistics, Qingdao University, Qingdao 266071, China)

  • Dan Xue

    (School of Mathematics and Statistics, Qingdao University, Qingdao 266071, China)

  • Yujia Zhai

    (School of Mathematics and Statistics, Qingdao University, Qingdao 266071, China)

Abstract

In this paper, we propose a stochastic primal-dual adaptive method based on an inexact augmented Lagrangian function to solve non-convex programs, referred to as the SPDAM. Different from existing methods, SPDAM incorporates adaptive step size and momentum-based search directions, which improve the convergence rate. At each iteration, an inexact augmented Lagrangian subproblem is solved to update the primal variables. A post-processing step is designed to adjust the primal variables to meet the accuracy requirement, and the adjusted primal variable is used to compute the dual variable. Under appropriate assumptions, we prove that the method converges to the ε -KKT point of the primal problem, and a complexity result of SPDAM less than O ( ε − 11 2 ) is established. This is better than the most famous O ( ε − 6 ) result. The numerical experimental results validate that this method outperforms several existing methods with fewer iterations and a lower running time.

Suggested Citation

  • Rulei Qi & Dan Xue & Yujia Zhai, 2024. "A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints," Mathematics, MDPI, vol. 12(15), pages 1-26, July.
  • Handle: RePEc:gam:jmathe:v:12:y:2024:i:15:p:2393-:d:1447312
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/12/15/2393/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/12/15/2393/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Lingzi Jin & Xiao Wang, 2022. "A stochastic primal-dual method for a class of nonconvex constrained optimization," Computational Optimization and Applications, Springer, vol. 83(1), pages 143-180, September.
    2. Yingjie Tian & Yuqi Zhang & Haibin Zhang, 2023. "Recent Advances in Stochastic Gradient Descent in Deep Learning," Mathematics, MDPI, vol. 11(3), pages 1-23, January.
    Full references (including those not matched with items on IDEAS)

    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. Seung-Hwan Lee & Sung-Hak Lee, 2024. "U-Net-Based Learning Using Enhanced Lane Detection with Directional Lane Attention Maps for Various Driving Environments," Mathematics, MDPI, vol. 12(8), pages 1-24, April.
    2. Cong Shen & Wei Zhang & Tanping Zhou & Lingling Zhang, 2024. "A Security-Enhanced Federated Learning Scheme Based on Homomorphic Encryption and Secret Sharing," Mathematics, MDPI, vol. 12(13), pages 1-20, June.
    3. Vasiliki Rokani & Stavros D. Kaminaris & Petros Karaisas & Dimitrios Kaminaris, 2023. "Power Transformer Fault Diagnosis Using Neural Network Optimization Techniques," Mathematics, MDPI, vol. 11(22), pages 1-33, November.

    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:12:y:2024:i:15:p:2393-:d:1447312. 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.