On the optimality of Orthogonal Greedy Algorithm for M-coherent dictionaries
arXiv:1003.53493 citationsh-index: 7
Originality Synthesis-oriented
AI Analysis
Provides theoretical justification for OGA's effectiveness in sparse approximation, relevant to signal processing and machine learning communities.
The paper proves that Orthogonal Greedy Algorithm (OGA) achieves near-optimal approximation within the first 1/(20M) steps for M-coherent dictionaries, establishing theoretical guarantees for its performance.
We show that Orthogonal Greedy Algorithms (Orthogonal Matching Pursuit) provides almost optimal approximation on the first [1/(20M)] steps for M-coherent dictionaries