Accéder directement au contenu Accéder directement à la navigation
Pré-publication, Document de travail

Sketching Datasets for Large-Scale Learning (long version)

Abstract : This article considers "sketched learning," or "compressive learning," an approach to large-scale machine learning where datasets are massively compressed before learning (e.g., clustering, classification, or regression) is performed. In particular, a "sketch" is first constructed by computing carefully chosen nonlinear random features (e.g., random Fourier features) and averaging them over the whole dataset. Parameters are then learned from the sketch, without access to the original dataset. This article surveys the current state-of-the-art in sketched learning, including the main concepts and algorithms, their connections with established signal-processing methods, existing theoretical guarantees-on both information preservation and privacy preservation, and important open problems.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

https://hal.inria.fr/hal-02909766
Contributeur : Rémi Gribonval <>
Soumis le : mardi 4 août 2020 - 21:34:09
Dernière modification le : samedi 30 janvier 2021 - 03:08:18
Archivage à long terme le : : lundi 30 novembre 2020 - 12:34:41

Fichier

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02909766, version 1
  • ARXIV : 2008.01839

Citation

Rémi Gribonval, Antoine Chatalic, Nicolas Keriven, Vincent Schellekens, Laurent Jacques, et al.. Sketching Datasets for Large-Scale Learning (long version). 2020. ⟨hal-02909766v1⟩

Partager

Métriques

Consultations de la notice

140

Téléchargements de fichiers

110