Concentration of the Frobenius norms of generalized matrix inverses - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Concentration of the Frobenius norms of generalized matrix inverses

Résumé

In many applications it is useful to replace the Moore-Penrose pseudoinverse (MPP) by another generalized inverse with more favorable properties. We may want, for example, to have many zero entries, but without giving up too much of the stability of the MPP. One way to quantify stability is to look at how much the Frobenius norm of a generalized inverse exceeds that of the MPP. In this paper we derive finite-size concentration bounds for the Frobenius norm of p-minimal general inverses of iid Gaussian matrices, with 1 ≤ p ≤ 2. For p = 1 we prove exponential concentration of the Frobenius norm of the sparse pseudoinverse; for p = 2, we get similar results for the MPP. Our proof is based on the convex Gaussian min-max theorem, but unlike previous applications we give finite-size concentration results which required development of new techniques.
Fichier principal
Vignette du fichier
pseudo-part2.pdf (700.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01897046 , version 1 (17-10-2018)
hal-01897046 , version 2 (22-11-2018)

Identifiants

Citer

Ivan Dokmanić, Rémi Gribonval. Concentration of the Frobenius norms of generalized matrix inverses. 2018. ⟨hal-01897046v1⟩
226 Consultations
1054 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More