Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling - Inria - Institut national de recherche en sciences et technologies du numérique
Journal Articles Mathematical Statistics and Learning Year : 2021

Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling

Abstract

We provide statistical learning guarantees for two unsupervised learning tasks in the context of compressive statistical learning, a general framework for resource-efficient large-scale learning that we introduced in a companion paper.The principle of compressive statistical learning is to compress a training collection, 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. We explicitly describe and analyze random feature functions which empirical averages preserve the needed information for compressive clustering and compressive Gaussian mixture modeling with fixed known variance, and establish sufficient sketch sizes given the problem dimensions.
Fichier principal
Vignette du fichier
Compressive_learning_part2_sanitized_source.pdf (845.31 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02536818 , version 1 (16-04-2020)
hal-02536818 , version 2 (11-06-2021)
hal-02536818 , version 3 (16-08-2021)

Identifiers

Cite

Rémi Gribonval, Gilles Blanchard, Nicolas Keriven, Yann Traonmilin. Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling. Mathematical Statistics and Learning, 2021, 3 (2), pp.165-257. ⟨10.4171/msl/21⟩. ⟨hal-02536818v3⟩
421 View
454 Download

Altmetric

Share

More