IDEAS home Printed from https://ideas.repec.org/a/taf/tsysxx/v57y2026i6p1485-1505.html

A decentralised strongly adaptive subgradient online learning algorithm over time-varying networks

Author

Listed:
  • Guoyong Wang
  • Moli Zhang
  • Lin Wang
  • Xuhui Zhao
  • Qilin Zhang

Abstract

Recently, centralised adaptive gradient methods have been successfully utilised in many significant applications. However, the design and convergence analysis of decentralised adaptive gradient methods under strong convexity remains an open problem. To fill the gap, this paper proposes a decentralised strongly adaptive subgradient online learning algorithm over time-varying networks, called DS-AdaBoundNc. Moreover, we rigorously prove that the logarithmic regret bound is achieved by exploiting strong convexity for DS-AdaBoundNc. Finally, the performance of DS-AdaBoundNc is evaluated through various experiments on different long-tested datasets. The results show that the DS-AdaBoundNc outperforms current state-of-the-art decentralised online learning methods under strong convexity. In addition, the generalisation ability of DS-AdaBoundNc is also superior to baseline algorithms.

Suggested Citation

  • Guoyong Wang & Moli Zhang & Lin Wang & Xuhui Zhao & Qilin Zhang, 2026. "A decentralised strongly adaptive subgradient online learning algorithm over time-varying networks," International Journal of Systems Science, Taylor & Francis Journals, vol. 57(6), pages 1485-1505, April.
    • Handle: RePEc:taf:tsysxx:v:57:y:2026:i:6:p:1485-1505
    DOI: 10.1080/00207721.2025.2530672
    as

    Download full text from publisher

    File URL: http://hdl.handle.net/10.1080/00207721.2025.2530672
    Download Restriction: Access to full text is restricted to subscribers.
    File URL: https://libkey.io/10.1080/00207721.2025.2530672?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

    for a different version of it.

    More about this item

    Statistics

    Access and download statistics

    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:taf:tsysxx:v:57:y:2026:i:6:p:1485-1505. 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: Chris Longhurst (email available below). General contact details of provider: http://www.tandfonline.com/TSYS20 .

    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.