Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding

The celebrated sparse representation model has led to remarkable results in various signal processing tasks in the last decade. However, despite its initial purpose of serving as a global prior for entire signals, it has been commonly used for modeling low dimensional patches due to the computationa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on signal processing Ročník 65; číslo 21; s. 5687 - 5701
Hlavní autoři: Papyan, Vardan, Sulam, Jeremias, Elad, Michael
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.11.2017
Témata:
basis pursuit
Computational modeling
Convolution
Convolutional codes
convolutional sparse coding
Dictionaries
global modeling
local processing
Matching pursuit algorithms
Mathematical model
orthogonal matching pursuit
Sparse matrices
Sparse representations
stability guarantees
uniqueness guarantees
ISSN:1053-587X, 1941-0476
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The celebrated sparse representation model has led to remarkable results in various signal processing tasks in the last decade. However, despite its initial purpose of serving as a global prior for entire signals, it has been commonly used for modeling low dimensional patches due to the computational constraints it entails when deployed with learned dictionaries. A way around this problem has been recently proposed, adopting a convolutional sparse representation model. This approach assumes that the global dictionary is a concatenation of banded circulant matrices. While several works have presented algorithmic solutions to the global pursuit problem under this new model, very few truly effective guarantees are known for the success of such methods. In this paper, we address the theoretical aspects of the convolutional sparse model providing the first meaningful answers to questions of uniqueness of solutions and success of pursuit algorithms, both greedy and convex relaxations, in ideal and noisy regimes. To this end, we generalize mathematical quantities, such as the l 0 norm, mutual coherence, Spark and restricted isometry property to their counterparts in the convolutional setting, intrinsically capturing local measures of the global model. On the algorithmic side, we demonstrate how to solve the global pursuit problem by using simple local processing, thus offering a first of its kind bridge between global modeling of signals and their patch-based local treatment.
ISSN:1053-587X
1941-0476
DOI:10.1109/TSP.2017.2733447