IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v11y2020i1d10.1038_s41467-020-14663-9.html
   My bibliography  Save this article

Complexity control by gradient descent in deep networks

Author

Listed:
  • Tomaso Poggio

    (MIT)

  • Qianli Liao

    (MIT)

  • Andrzej Banburski

    (MIT)

Abstract

Overparametrized deep networks predict well, despite the lack of an explicit complexity control during training, such as an explicit regularization term. For exponential-type loss functions, we solve this puzzle by showing an effective regularization effect of gradient descent in terms of the normalized weights that are relevant for classification.

Suggested Citation

  • Tomaso Poggio & Qianli Liao & Andrzej Banburski, 2020. "Complexity control by gradient descent in deep networks," Nature Communications, Nature, vol. 11(1), pages 1-5, December.
    • Handle: RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-14663-9
    DOI: 10.1038/s41467-020-14663-9
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-020-14663-9
    File Function: Abstract
    Download Restriction: no
    File URL: https://libkey.io/10.1038/s41467-020-14663-9?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
    ---><---

    Citations

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


    Cited by:

    1. Duan, Jikai & Chang, Mingheng & Chen, Xiangyue & Wang, Wenpeng & Zuo, Hongchao & Bai, Yulong & Chen, Bolong, 2022. "A combined short-term wind speed forecasting model based on CNN–RNN and linear regression optimization considering error," Renewable Energy, Elsevier, vol. 200(C), pages 788-808.

    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:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-14663-9. 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: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.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.