Beyond Moore-Penrose Part II: The Sparse Pseudoinverse

Abstract : This is the second part of a two-paper series on generalized inverses that minimize matrix norms. In Part II we focus on generalized inverses that are minimizers of entrywise p norms whose main representative is the sparse pseudoinverse for $p = 1$. We are motivated by the idea to replace the Moore-Penrose pseudoinverse by a sparser generalized inverse which is in some sense well-behaved. Sparsity implies that it is faster to apply the resulting matrix; well-behavedness would imply that we do not lose much in stability with respect to the least-squares performance of the MPP. We first address questions of uniqueness and non-zero count of (putative) sparse pseu-doinverses. We show that a sparse pseudoinverse is generically unique, and that it indeed reaches optimal sparsity for almost all matrices. We then turn to proving our main stability result: finite-size concentration bounds for the Frobenius norm of p-minimal inverses for $1 ≤ p ≤ 2$. Our proof is based on tools from convex analysis and random matrix theory, in particular the recently developed convex Gaussian min-max theorem. Along the way we prove several results about sparse representations and convex programming that were known folklore, but of which we could find no proof.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger
Contributeur : Rémi Gribonval <>
Soumis le : jeudi 13 juillet 2017 - 23:28:04
Dernière modification le : mercredi 16 mai 2018 - 11:24:14
Document(s) archivé(s) le : vendredi 26 janvier 2018 - 20:09:39


  • HAL Id : hal-01547283, version 2
  • ARXIV : 1706.08701


Ivan Dokmanić, Rémi Gribonval. Beyond Moore-Penrose Part II: The Sparse Pseudoinverse. 2017. 〈hal-01547283v2〉



Consultations de la notice


Téléchargements de fichiers