Average performance of Orthogonal Matching Pursuit (OMP) for sparse approximation

09/18/2018
by   Karin Schnass, et al.
0

We present a theoretical analysis of the average performance of OMP for sparse approximation. For signals, that are generated from a dictionary with K atoms and coherence μ and coefficients corresponding to a geometric sequence with parameter α, we show that OMP is successful with high probability as long as the sparsity level S scales as Sμ^2 K ≲ 1-α . This improves by an order of magnitude over worst case results and shows that OMP and its famous competitor Basis Pursuit outperform each other depending on the setting.

READ FULL TEXT

page 9

page 10

research
02/21/2011

Improved RIP Analysis of Orthogonal Matching Pursuit

Orthogonal Matching Pursuit (OMP) has long been considered a powerful he...
research
10/03/2010

Convolutional Matching Pursuit and Dictionary Training

Matching pursuit and K-SVD is demonstrated in the translation invariant ...
research
07/15/2023

Sharp Convergence Rates for Matching Pursuit

We study the fundamental limits of matching pursuit, or the pure greedy ...
research
07/18/2020

A Quasi-Orthogonal Matching Pursuit Algorithm for Compressive Sensing

In this paper, we propose a new orthogonal matching pursuit algorithm ca...
research
04/13/2018

On the Minimal Overcompleteness Allowing Universal Sparse Representation

Sparse representation over redundant dictionaries constitutes a good mod...
research
06/16/2023

Samplet basis pursuit

We consider kernel-based learning in samplet coordinates with l1-regular...
research
06/07/2018

Performance of Hierarchical Sparse Detectors for Massive MTC

Recently, the Hierarchical Hard Thresholding Pursuit (HiHTP) algorithm w...

Please sign up or login with your details

Forgot password? Click here to reset