Principal Component Analysis for Multivariate Extremes - Laboratoire Traitement et Communication de l'Information Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Principal Component Analysis for Multivariate Extremes

Résumé

The first order behavior of multivariate heavy-tailed random vectors above large radial thresholds is ruled by a limit measure in a regular variation framework. For a high dimensional vector, a reasonable assumption is that the support of this measure is concentrated on a lower dimensional subspace, meaning that certain linear combinations of the components are much likelier to be large than others. Identifying this subspace and thus reducing the dimension will facilitate a refined statistical analysis. In this work we apply Principal Component Analysis (PCA) to a re-scaled version of radially thresholded observations. Within the statistical learning framework of empirical risk minimization, our main focus is to analyze the squared reconstruction error for the exceedances over large radial thresholds. We prove that the empirical risk converges to the true risk, uniformly over all projection subspaces. As a consequence, the best projection subspace is shown to converge in probability to the optimal one, in terms of the Hausdorff distance between their intersections with the unit sphere. In addition, if the exceedances are re-scaled to the unit ball, we obtain finite sample uniform guarantees to the reconstruction error pertaining to the estimated projection sub-space. Numerical experiments illustrate the relevance of the proposed framework for practical purposes.
Fichier principal
Vignette du fichier
PCA_final_arxiv.pdf (426.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02164305 , version 1 (25-06-2019)

Identifiants

Citer

Holger Drees, Anne Sabourin. Principal Component Analysis for Multivariate Extremes. 2019. ⟨hal-02164305v1⟩
61 Consultations
190 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More