# Sample Complexity of Dictionary Learning and other Matrix Factorizations

1 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Many modern tools in machine learning and signal processing, such as sparse dictionary learning, principal component analysis (PCA), non-negative matrix factorization (NMF), $K$-means clustering, etc., rely on the factorization of a matrix obtained by concatenating high-dimensional vectors from a training collection. While the idealized task would be to optimize the expected quality of the factors over the underlying distribution of training vectors, it is achieved in practice by minimizing an empirical average over the considered collection. The focus of this paper is to provide sample complexity estimates to uniformly control how much the empirical average deviates from the expected cost function. Standard arguments imply that the performance of the empirical predictor also exhibit such guarantees. The level of genericity of the approach encompasses several possible constraints on the factors (tensor product structure, shift-invariance, sparsity \ldots), thus providing a unified perspective on the sample complexity of several widely used matrix factorization schemes. The derived generalization bounds behave proportional to $\sqrt{\log(n)/n}$ w.r.t.\ the number of samples $n$ for the considered matrix factorization techniques.
Keywords :
Document type :
Journal articles
Domain :

https://hal.inria.fr/hal-00918142
Contributor : Rémi Gribonval Connect in order to contact the contributor
Submitted on : Wednesday, April 8, 2015 - 10:54:55 PM
Last modification on : Monday, July 25, 2022 - 3:28:14 AM
Long-term archiving on: : Thursday, July 9, 2015 - 10:55:21 AM

### Files

sample_complexity_matrix_facto...
Files produced by the author(s)

### Citation

Rémi Gribonval, Rodolphe Jenatton, Francis Bach, Martin Kleinsteuber, Matthias Seibert. Sample Complexity of Dictionary Learning and other Matrix Factorizations. IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2015, 61 (6), pp.3469-3486. ⟨10.1109/TIT.2015.2424238⟩. ⟨hal-00918142v3⟩

Record views