Compressive k-Means with Differential Privacy - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Compressive k-Means with Differential Privacy

Abstract

In the compressive learning framework, one harshly compresses a whole training dataset into a single vector of generalized random moments, the sketch, from which a learning task can subsequently be performed. We prove that this loss of information can be leveraged to design a differentially private mechanism, and study empirically the privacy-utility tradeoff for the k-means clustering problem.
Fichier principal
Vignette du fichier
spars_final.pdf (341.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02154820 , version 1 (13-06-2019)

Identifiers

  • HAL Id : hal-02154820 , version 1

Cite

Vincent Schellekens, Antoine Chatalic, Florimond Houssiau, Yves-Alexandre de Montjoye, Laurent Jacques, et al.. Compressive k-Means with Differential Privacy. SPARS 2019 - Signal Processing with Adaptive Sparse Structured Representations, Jul 2019, Toulouse, France. pp.1-2. ⟨hal-02154820⟩
168 View
230 Download

Share

Gmail Facebook Twitter LinkedIn More