Sparse and spurious: dictionary learning with noise and outliers - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Information Theory Year : 2015

Sparse and spurious: dictionary learning with noise and outliers


A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only been a few theoretical arguments supporting these evidences. In particular, sparse coding, or sparse dictionary learning, relies on a non-convex procedure whose local minima have not been fully analyzed yet. In this paper, we consider a probabilistic model of sparse signals, and show that, with high probability, sparse coding admits a local minimum around the reference dictionary generating the signals. Our study takes into account the case of over-complete dictionaries, noisy signals, and possible outliers, thus extending previous work limited to noiseless settings and/or under-complete dictionaries. The analysis we conduct is non-asymptotic and makes it possible to understand how the key quantities of the problem, such as the coherence or the level of noise, can scale with respect to the dimension of the signals, the number of atoms, the sparsity and the number of observations.
Fichier principal
Vignette du fichier
sparse_and_spurious.pdf (420.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01025503 , version 1 (18-07-2014)
hal-01025503 , version 2 (05-08-2014)
hal-01025503 , version 3 (04-09-2014)
hal-01025503 , version 4 (21-08-2015)



Rémi Gribonval, Rodolphe Jenatton, Francis Bach. Sparse and spurious: dictionary learning with noise and outliers. IEEE Transactions on Information Theory, 2015, 61 (11), pp.6298-6319. ⟨10.1109/TIT.2015.2472522⟩. ⟨hal-01025503v4⟩
1534 View
1689 Download



Gmail Facebook X LinkedIn More