Compressive Statistical Learning with Random Feature Moments - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Mathematical Statistics and Learning Year : 2021

Compressive Statistical Learning with Random Feature Moments

Abstract

We describe a general framework --compressive statistical learning-- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. A near-minimizer of the risk is computed from the sketch through the solution of a nonlinear least squares problem. We investigate sufficient sketch sizes to control the generalization error of this procedure. The framework is illustrated on compressive PCA, compressive clustering, and compressive Gaussian mixture Modeling with fixed known variance. The latter two are further developed in a companion paper.
Fichier principal
Vignette du fichier
Compressive_learning_sanitized_source.pdf (644.64 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01544609 , version 1 (21-06-2017)
hal-01544609 , version 2 (06-12-2017)
hal-01544609 , version 3 (16-04-2020)
hal-01544609 , version 4 (23-03-2021)
hal-01544609 , version 5 (21-06-2021)

Identifiers

Cite

Rémi Gribonval, Gilles Blanchard, Nicolas Keriven, Yann Traonmilin. Compressive Statistical Learning with Random Feature Moments. Mathematical Statistics and Learning, 2021, 3 (2), pp.113-164. ⟨10.4171/msl/20⟩. ⟨hal-01544609v5⟩
1289 View
1164 Download

Altmetric

Share

Gmail Facebook X LinkedIn More