Compressive statistical learning with random feature moments

  • Rémi Gribonval

    Université de Lyon, France
  • Gilles Blanchard

    Université Paris-Saclay, Orsay, France
  • Nicolas Keriven

    CNRS, GIPSA-lab, UMR 5216, Saint-Martin-d’Hères, France
  • Yann Traonmilin

    CNRS, Université de Bordeaux, Talence, France
Compressive statistical learning with random feature moments cover

A subscription is required to access this article.

Abstract

We describe a general framework — — for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional (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.

Cite this article

Rémi Gribonval, Gilles Blanchard, Nicolas Keriven, Yann Traonmilin, Compressive statistical learning with random feature moments. Math. Stat. Learn. 3 (2020), no. 2, pp. 113–164

DOI 10.4171/MSL/20