IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2012.13121.html
   My bibliography  Save this paper

Memory-Gated Recurrent Networks

Author

Listed:
  • Yaquan Zhang
  • Qi Wu
  • Nanbo Peng
  • Min Dai
  • Jing Zhang
  • Hu Wang

Abstract

The essence of multivariate sequential learning is all about how to extract dependencies in data. These data sets, such as hourly medical records in intensive care units and multi-frequency phonetic time series, often time exhibit not only strong serial dependencies in the individual components (the "marginal" memory) but also non-negligible memories in the cross-sectional dependencies (the "joint" memory). Because of the multivariate complexity in the evolution of the joint distribution that underlies the data generating process, we take a data-driven approach and construct a novel recurrent network architecture, termed Memory-Gated Recurrent Networks (mGRN), with gates explicitly regulating two distinct types of memories: the marginal memory and the joint memory. Through a combination of comprehensive simulation studies and empirical experiments on a range of public datasets, we show that our proposed mGRN architecture consistently outperforms state-of-the-art architectures targeting multivariate time series.

Suggested Citation

  • Yaquan Zhang & Qi Wu & Nanbo Peng & Min Dai & Jing Zhang & Hu Wang, 2020. "Memory-Gated Recurrent Networks," Papers 2012.13121, arXiv.org, revised Dec 2020.
    • Handle: RePEc:arx:papers:2012.13121
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2012.13121
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Xing Yan & Qi Wu & Wen Zhang, 2019. "Cross-sectional Learning of Extremal Dependence among Financial Assets," Papers 1905.13425, arXiv.org, revised Oct 2019.
    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. Siyi Wang & Xing Yan & Bangqi Zheng & Hu Wang & Wangli Xu & Nanbo Peng & Qi Wu, 2021. "Risk and return prediction for pricing portfolios of non-performing consumer credit," Papers 2110.15102, arXiv.org.
    2. Chuting Sun & Qi Wu & Xing Yan, 2023. "Dynamic CVaR Portfolio Construction with Attention-Powered Generative Factor Learning," Papers 2301.07318, arXiv.org, revised Jan 2024.
    3. Xiangqian Sun & Xing Yan & Qi Wu, 2020. "Generative Learning of Heterogeneous Tail Dependence," Papers 2011.13132, arXiv.org, revised Nov 2023.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    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:arx:papers:2012.13121. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.