An improved theoretical analysis of convolutional sparse coding using stripe coherence

Convolutional sparse coding has proven to be very effective in a wide range of applications. Recent work addressed the theoretical performance of global orthogonal matching pursuit (OMP) using the stripe coherence that is a stronger characterization of the convolutional dictionary. In this paper, we...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of computational and applied mathematics Ročník 469; s. 116631
Hlavní autoři: Li, Haifeng, Chen, Wengu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.12.2025
Témata:
Convolutional sparse coding
Sparse signal recovery
Stability guarantees
Stripe coherence
Sparse signal recovery
Stripe coherence
Stability guarantees
Convolutional sparse coding
ISSN:0377-0427
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Convolutional sparse coding has proven to be very effective in a wide range of applications. Recent work addressed the theoretical performance of global orthogonal matching pursuit (OMP) using the stripe coherence that is a stronger characterization of the convolutional dictionary. In this paper, we further provide the theoretical analysis of convolutional sparse model. Our result improves the guarantee condition for global OMP based on convolutional sparse model. We also provide the theoretical guarantee for basis pursuit using stripe coherence based on convolutional sparse model, which is absent in the existing results.
ISSN:0377-0427
DOI:10.1016/j.cam.2025.116631