Basis Identification from Random Sparse Samples - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Basis Identification from Random Sparse Samples

Karin Schnass
  • Function : Author


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.
Fichier principal
Vignette du fichier
56.pdf (141.23 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00369562 , version 1 (24-03-2009)


  • 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⟩
149 View
136 Download


Gmail Facebook X LinkedIn More