Abstract | ||
---|---|---|
In this paper, we study the problem of decomposing a superposition of a low-rank matrix and a sparse matrix when a relatively few linear measurements are available. This problem arises in many data processing tasks such as aligning multiple images or rectifying regular texture, where the goal is to recover a low-rank matrix with a large fraction of corrupted entries in the presence of nonlinear domain transformation. We consider a natural convex heuristic to this problem which is a variant to the recently proposed Principal Component Pursuit. We prove that under suitable conditions, this convex program guarantees to recover the correct low-rank and sparse components despite reduced measurements. Our analysis covers both random and deterministic measurement models. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ISIT.2012.6283063 | international symposium on information theory |
Keywords | Field | DocType |
data handling,principal component analysis,sparse matrices,task analysis,data processing tasks,low-rank matrix,nonlinear domain transformation,principal component pursuit,reduced linear measurements,sparse matrix | Sparse PCA,Combinatorics,Computer science,Matrix (mathematics),Sparse approximation,Single-entry matrix,Principal component analysis,Eigenvalues and eigenvectors,Sparse matrix,Matrix-free methods | Journal |
Volume | ISSN | ISBN |
abs/1202.6445 | 2157-8095 E-ISBN : 978-1-4673-2578-3 | 978-1-4673-2578-3 |
Citations | PageRank | References |
16 | 0.76 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arvind Ganesh | 1 | 4904 | 153.80 |
Kerui Min | 2 | 103 | 5.33 |
John Wright | 3 | 10974 | 361.48 |
Yi Ma | 4 | 14931 | 536.21 |