Partial Hard Thresholding

We study iterative algorithms for compressed sensing that have an "orthogonalization" step at each iteration to keep the residual orthogonal to the span of those columns of the measurement matrix that have been selected so far. To unify the design and analysis of such algorithms, we propos...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on information theory Ročník 63; číslo 5; s. 3029 - 3038
Hlavní autoři: Jain, Prateek, Tewari, Ambuj, Dhillon, Inderjit S.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.05.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Classification algorithms
Columns (structural)
Compressed sensing
Greedy algorithms
Iterative algorithms
iterative thresholding algorithms
Matching pursuit algorithms
Minimization
Optimization techniques
Recovery
restricted isometry property
Sparse matrices
sparse recovery
ISSN:0018-9448, 1557-9654
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We study iterative algorithms for compressed sensing that have an "orthogonalization" step at each iteration to keep the residual orthogonal to the span of those columns of the measurement matrix that have been selected so far. To unify the design and analysis of such algorithms, we propose a novel partial hard-thresholding (PHT) operator that is similar to the hard thresholding operator but restricts the amount by which the support set can change in one iteration. Using the PHT operator and its properties, we provide a general framework to prove support recovery results for iterative algorithms employing this operator as well as those employing the hard-thresholding operator. Next, based on the PHT operator, we propose a novel family of algorithms. At one end of our family of algorithms lie well-known hard thresholding algorithms iterative thresholding with inversion and hard thresholding pursuit, whereas at the other end, we get a novel algorithm that we call orthogonal matching pursuit with replacement (OMPR). Like the classic greedy algorithm OMP, OMPR too adds exactly one coordinate to the support of the iterate at each iteration based on the correlation with the current residual. However, unlike OMP, OMPR also removes one coordinate from the support. This simple change allows us to prove that OMPR has the best known guarantees for sparse recovery in terms of the restricted isometry property (RIP), a condition on the measurement matrix. In contrast, OMP is known to have very weak performance guarantees under RIP. Finally, we show that most of the existing "orthogonalized" iterative algorithms, such as CoSaMP, subspace pursuit, OMP, can be expressed using the PHT operator. As a pleasing consequence of our novel and generic results for the PHT operator, we provide the tightest known RIP analysis of all of the above-mentioned iterative algorithms: CoSaMP, subspace pursuit, and OMP.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9448
1557-9654
DOI:10.1109/TIT.2017.2686880