Skip to Main content Skip to Navigation
Conference papers

Projections aléatoires pour l'apprentissage compressif

Abstract : Compressive learning is a framework to drastically compress the volume of large training collections while preserving the information needed to learn. Guided by unsupervised learning examples, we survey the involved tools, the existing theoretical guarantees both in terms of information preservation and of privacy preservation, and conclude with some open problems.
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-02154803
Contributor : Antoine Chatalic <>
Submitted on : Thursday, June 13, 2019 - 9:05:04 AM
Last modification on : Tuesday, September 22, 2020 - 3:45:49 AM

File

gretsi-19_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02154803, version 1

Citation

Antoine Chatalic, Nicolas Keriven, Rémi Gribonval. Projections aléatoires pour l'apprentissage compressif. GRETSI 2019 − XXVIIème Colloque francophone de traitement du signal et des images, Aug 2019, Lille, France. pp.1-4. ⟨hal-02154803⟩

Share

Metrics

Record views

324

Files downloads

826