Performance Guarantees for Schatten-pp Quasi-Norm Minimization in Recovery of Low-Rank Matrices

preprint2014arXivOpen access

Abstract

We address some theoretical guarantees for Schatten-pp quasi-norm minimization (p∈(0,1]p \in (0,1]) in recovering low-rank matrices from compressed linear measurements. Firstly, using null space properties of the measurement operator, we provide a sufficient condition for exact recovery of low-rank matrices. This condition guarantees unique recovery of matrices of ranks equal or larger than what is guaranteed by nuclear norm minimization. Secondly, this sufficient condition leads to a theorem proving that all restricted isometry property (RIP) based sufficient conditions for ℓp\ell_p quasi-norm minimization generalize to Schatten-pp quasi-norm minimization. Based on this theorem, we provide a few RIP-based recovery conditions.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.