Jointly Low-Rank and Bisparse Recovery: Questions and Partial Answers - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Analysis and Applications Année : 2020

Jointly Low-Rank and Bisparse Recovery: Questions and Partial Answers

Résumé

We investigate the problem of recovering jointly $r$-rank and $s$-bisparse matrices from as few linear measurements as possible, considering arbitrary measurements as well as rank-one measurements. In both cases, we show that $m \asymp r s \ln(en/s)$ measurements make the recovery possible in theory, meaning via a nonpractical algorithm. In case of arbitrary measurements, we investigate the possibility of achieving practical recovery via an iterative-hard-thresholding algorithm when $m \asymp r s^\gamma \ln(en/s)$ for some exponent $\gamma>0$. We show that this is feasible for $\gamma=2$ and that the proposed analysis cannot cover the case $\gamma \leq 1$. The precise value of the optimal exponent $\gamma \in [1,2]$ is the object of a question, raised but unresolved in this paper, about head projections for the jointly low-rank and bisparse structure. Some related questions are partially answered in passing. For the rank-one measurements, we suggest on arcane grounds an iterative-hard-thresholding algorithm modified to exploit the nonstandard restricted isometry property obeyed by this type of measurements.
Fichier principal
Vignette du fichier
main.pdf (199.05 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02062891 , version 1 (11-03-2019)
hal-02062891 , version 2 (25-10-2019)

Identifiants

Citer

Simon Foucart, Rémi Gribonval, Laurent Jacques, Holger Rauhut. Jointly Low-Rank and Bisparse Recovery: Questions and Partial Answers. Analysis and Applications, 2020, 18 (01), pp.25--48. ⟨10.1142/S0219530519410094⟩. ⟨hal-02062891v2⟩
287 Consultations
201 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More