Sketching Datasets for Large-Scale Learning (long version) - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Sketching Datasets for Large-Scale Learning (long version)

(1, 2) , (1) , (3) , (4) , (4) , (5)
1
2
3
4
5

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.
Fichier principal
Vignette du fichier
SPM_paper.pdf (7.94 Mo) Télécharger le fichier
Vignette du fichier
SPM_paper.bcf (108.64 Ko) Télécharger le fichier
Vignette du fichier
SPM_paper.run.xml (2.36 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02909766 , version 1 (04-08-2020)
hal-02909766 , version 2 (26-01-2021)

Identifiers

Cite

Rémi Gribonval, Antoine Chatalic, Nicolas Keriven, Vincent Schellekens, Laurent Jacques, et al.. Sketching Datasets for Large-Scale Learning (long version). 2021. ⟨hal-02909766v2⟩
254 View
126 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More