IDEAS home Printed from https://ideas.repec.org/a/inm/oropre/v71y2023i2p649-664.html
   My bibliography  Save this article

Distributionally Robust Losses for Latent Covariate Mixtures

Author

Listed:
  • John Duchi

    (Departments of Electrical Engineering and Statistics, Stanford University, Stanford, California 94305)

  • Tatsunori Hashimoto

    (Department of Computer Science, Stanford University, Stanford, California 94305)

  • Hongseok Namkoong

    (Decision, Risk, and Operations Division, Columbia Business School, New York, New York 10027)

Abstract

While modern large-scale data sets often consist of heterogeneous subpopulations—for example, multiple demographic groups or multiple text corpora—the standard practice of minimizing average loss fails to guarantee uniformly low losses across all subpopulations. We propose a convex procedure that controls the worst case performance over all subpopulations of a given size. Our procedure comes with finite-sample (nonparametric) convergence guarantees on the worst-off subpopulation. Empirically, we observe on lexical similarity, wine quality, and recidivism prediction tasks that our worst case procedure learns models that do well against unseen subpopulations.

Suggested Citation

  • John Duchi & Tatsunori Hashimoto & Hongseok Namkoong, 2023. "Distributionally Robust Losses for Latent Covariate Mixtures," Operations Research, INFORMS, vol. 71(2), pages 649-664, March.
    • Handle: RePEc:inm:oropre:v:71:y:2023:i:2:p:649-664
    DOI: 10.1287/opre.2022.2363
    as

    Download full text from publisher

    File URL: http://dx.doi.org/10.1287/opre.2022.2363
    Download Restriction: no
    File URL: https://libkey.io/10.1287/opre.2022.2363?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
    ---><---

    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:inm:oropre:v:71:y:2023:i:2:p:649-664. 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 Asher (email available below). General contact details of provider: https://edirc.repec.org/data/inforea.html .

    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.