Joint k-step analysis of Orthogonal Matching Pursuit and Orthogonal Least Squares

Abstract : Tropp's analysis of Orthogonal Matching Pursuit (OMP) using the Exact Recovery Condition (ERC) is extended to a first exact recovery analysis of Orthogonal Least Squares (OLS). We show that when the ERC is met, OLS is guaranteed to exactly recover the unknown support in at most k iterations where k denotes the support cardinality. Moreover, we provide a closer look at the analysis of both OMP and OLS when the ERC is not fulfilled. The existence of dictionaries for which some subsets are never recovered by OMP is proved. This phenomenon also appears with basis pursuit where support recovery depends on the sign patterns, but it does not occur for OLS. Finally, numerical experiments show that none of the considered algorithms is uniformly better than the other but for correlated dictionaries, guaranteed exact recovery may be obtained after fewer iterations for OLS than for OMP.
Document type :
Journal articles
IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers (IEEE), 2013, 59 (5), pp.3158-3174. <10.1109/TIT.2013.2238606>


https://hal.archives-ouvertes.fr/hal-00637003
Contributor : Charles Soussen <>
Submitted on : Tuesday, November 13, 2012 - 4:19:57 PM
Last modification on : Thursday, June 25, 2015 - 1:06:38 AM

File

erc_ols.pdf
fileSource_public_author

Identifiers

Collections

Citation

Charles Soussen, Rémi Gribonval, Jérôme Idier, Cédric Herzet. Joint k-step analysis of Orthogonal Matching Pursuit and Orthogonal Least Squares. IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers (IEEE), 2013, 59 (5), pp.3158-3174. <10.1109/TIT.2013.2238606>. <hal-00637003v2>

Export

Share

Metrics

Consultation de
la notice

464

Téléchargement du document

291