Skip to Main content Skip to Navigation
Conference papers

Exact recovery analysis of non-negative orthogonal matching pursuit

Abstract : It is well-known that Orthogonal Matching Pursuit (OMP) recovers the exact support of K-sparse signals under the condition µ < 1/(2K − 1) where µ denotes the mutual coherence of the dictionary. In this communication, we show that under the same condition and if the unknown K-sparse signal is non-negative, the weights of the atoms selected by OMP are non-negative at any of the first K iterations. Therefore, the generalized version of OMP to the non-negative setting (NNOMP) identifies with OMP, which allows us to establish an exact recovery analysis of NNOMP under the mutual coherence condition.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download
Contributor : El-Hadi Djermoune <>
Submitted on : Monday, November 25, 2019 - 12:33:08 PM
Last modification on : Wednesday, September 16, 2020 - 4:50:18 PM
Long-term archiving on: : Wednesday, February 26, 2020 - 5:08:11 PM


Files produced by the author(s)


  • HAL Id : hal-02378709, version 1


Thi Thanh Nguyen, Charles Soussen, Jérôme Idier, El-Hadi Djermoune. Exact recovery analysis of non-negative orthogonal matching pursuit. Signal Processing with Adaptive Sparse Structured Representations Workshop, SPARS 2019, Jul 2019, Toulouse, France. ⟨hal-02378709⟩



Record views


Files downloads