Skip to Main content Skip to Navigation
Conference papers

Dictionary Identifiability from Few Training Samples

Rémi Gribonval 1 Karin Schnass 2 
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This article treats the problem of learning a dictionary providing sparse representations for a given signal class, via L1 minimisation. The problem is to identify a dictionary Phi from a set of training samples Y knowing that Y = Phi.X for some coefficient matrix X. Using a characterisation of coefficient matrices X that allow to recover any orthonormal basis (ONB) as a local minimum of an L1 minimisation problem, it is shown that certain types of sparse random coefficient matrices will ensure local identifiability of the ONB with high probability, for a number of training samples which essentially grows linearly with the signal dimension.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Rémi Gribonval Connect in order to contact the contributor
Submitted on : Sunday, February 6, 2011 - 11:07:00 PM
Last modification on : Friday, February 4, 2022 - 3:24:59 AM
Long-term archiving on: : Saturday, May 7, 2011 - 2:26:13 AM


Files produced by the author(s)


  • HAL Id : inria-00544764, version 1


Rémi Gribonval, Karin Schnass. Dictionary Identifiability from Few Training Samples. European Signal Processing Conference (EUSIPCO'08), Aug 2008, Lausanne, Switzerland. ⟨inria-00544764⟩



Record views


Files downloads