IDEAS home Printed from https://ideas.repec.org/a/eee/stapro/v239y2026ics0167715226002828.html

Divergence-private query release and high-dimensional mean estimation

Author

Listed:
  • Deng, Fengnan
  • Vidyashankar, Anand N.

Abstract

We study privacy-preserving release of high-dimensional empirical queries under the power-divergence family, a one-parameter family of privacy constraints indexed by λ. The Hellinger member, corresponding to λ=−1/2, gives Hellinger differential privacy (HDP). The query-release problem considered here includes bounded scalar- and vector-valued empirical queries, such as means, linear statistics, histogram-type queries, and related empirical summaries, whose privacy calibrations are governed by global sensitivity. For Gaussian additive mechanisms, we derive a covariance-form calibration: privacy is equivalent to a Mahalanobis sensitivity bound, and in the isotropic case, the smallest admissible variance is cλ,ϵ{ΔL2(W)}2, where ΔL2(W) is the global ℓ2 sensitivity of the query W and cλ,ϵ is an explicit calibration constant. For any privacy level 0<ϵ<4 admissible across the family, cλ,ϵ is minimized at λ=−1/2.

Suggested Citation

  • Deng, Fengnan & Vidyashankar, Anand N., 2026. "Divergence-private query release and high-dimensional mean estimation," Statistics & Probability Letters, Elsevier, vol. 239(C).
  • Handle: RePEc:eee:stapro:v:239:y:2026:i:c:s0167715226002828
    DOI: 10.1016/j.spl.2026.110918
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0167715226002828
    Download Restriction: Full text may be restricted for ScienceDirect subscribers

    File URL: https://libkey.io/10.1016/j.spl.2026.110918?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

    Keywords

    ;
    ;
    ;
    ;
    ;

    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:eee:stapro:v:239:y:2026:i:c:s0167715226002828. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/622892/description#description .

    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.