General Mathematics

   

Low-Rank Matrix Recovery Via Regularized Nuclear Norm Minimization

Authors: Wendong Wang, Feng Zhang, Jianjun Wang

In this paper, we theoretically investigate the low-rank matrix recovery problem in the context of the unconstrained regularized nuclear norm minimization (RNNM) framework. Our theoretical findings show that, one can robustly recover any matrix X from its few noisy measurements b=A(X)+n with a bounded constraint ||n||_{2}<ε via the RNNM, if the linear map A satisfies restricted isometry property (RIP) with δ_{tk}<√(t-1)/t for certain fixed t>1. Recently, this condition with t≥4/3 has been proved by Cai and Zhang (2014) to be sharp for exactly recovering any rank-k matrices via the constrained nuclear norm minimization (NNM). To the best of our knowledge, our work first extends nontrivially this recovery condition for the constrained NNM to that for its unconstrained counterpart. Furthermore, it will be shown that similar recovery condition also holds for regularized l_{1}-norm minimization, which sometimes is also called Basis Pursuit DeNoising (BPDN).

Comments: 10 Pages.

Download: PDF

Submission history

[v1] 2018-10-08 22:09:22

Unique-IP document downloads: 16 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus