Skip to Main content Skip to Navigation
Conference papers

Basis Identification from Random Sparse 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 = \PhiX] for some coefficient matrix X. Using a characterisation of coefficient matrices X that allow to recover any basis 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 basis with high probability. The typically sufficient number of training samples grows up to a logarithmic factor linearly with the signal dimension.
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Ist Rennes Connect in order to contact the contributor
Submitted on : Tuesday, March 24, 2009 - 11:25:57 AM
Last modification on : Friday, February 4, 2022 - 3:22:08 AM
Long-term archiving on: : Thursday, June 10, 2010 - 5:40:02 PM


Files produced by the author(s)


  • HAL Id : inria-00369562, version 1


Rémi Gribonval, Karin Schnass. Basis Identification from Random Sparse Samples. SPARS'09 - Signal Processing with Adaptive Sparse Structured Representations, Inria Rennes - Bretagne Atlantique, Apr 2009, Saint Malo, France. ⟨inria-00369562⟩



Record views


Files downloads