Restricted isometry property of principal component pursuit with reduced linear measurements (Q2375728)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Restricted isometry property of principal component pursuit with reduced linear measurements |
scientific article |
Statements
Restricted isometry property of principal component pursuit with reduced linear measurements (English)
0 references
14 June 2013
0 references
Summary: The principal component pursuit with reduced linear measurements (PCP\_RLM) has gained great attention in applications, such as machine learning, video, and aligning multiple images. The recent research shows that strongly convex optimization for compressive principal component pursuit can guarantee the exact low-rank matrix recovery and sparse matrix recovery as well. In this paper, we prove that the operator of PCP\_RLM satisfies restricted isometry property (RIP) with high probability. In addition, we derive the bound of parameters depending only on observed quantities based on RIP property, which will guide us how to choose suitable parameters in strongly convex programming.
0 references
principal component pursuit with reduced linear measurements
0 references
compressive principal component pursuit
0 references
convex optimization
0 references
0 references
0 references
0 references