Normalized Iterative Hard Thresholding for Matrix Completion

Matrices of low rank can be uniquely determined from fewer linear measurements, or entries, than the total number of entries in the matrix. Moreover, there is a growing literature of computationally efficient algorithms which can recover a low rank matrix from such limited information; this process...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:SIAM journal on scientific computing Ročník 35; číslo 5; s. S104 - S125
Hlavní autoři: Tanner, Jared, Wei, Ke
Médium: Journal Article
Jazyk:angličtina
Vydáno: Philadelphia Society for Industrial and Applied Mathematics 01.01.2013
Témata:
Adaptive algorithms
Algorithms
Applied mathematics
Computational efficiency
Extreme values
Iterative methods
Masks
Mathematical analysis
Projection
ISSN:1064-8275, 1095-7197
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Matrices of low rank can be uniquely determined from fewer linear measurements, or entries, than the total number of entries in the matrix. Moreover, there is a growing literature of computationally efficient algorithms which can recover a low rank matrix from such limited information; this process is typically referred to as matrix completion. We introduce a particularly simple yet highly efficient alternating projection algorithm which uses an adaptive stepsize calculated to be exact for a restricted subspace. This method is proven to have near-optimal order recovery guarantees from dense measurement masks and is observed to have average case performance superior in some respects to other matrix completion algorithms for both dense measurement masks and entry measurements. In particular, this proposed algorithm is able to recover matrices from extremely close to the minimum number of measurements necessary. [PUBLICATION ABSTRACT]
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:1064-8275
1095-7197
DOI:10.1137/120876459