An Optimal Condition of Robust Low-rank Matrices Recovery

03/10/2020 ∙ by Jianwen Huang, et al. ∙ 0

In this paper we investigate the reconstruction conditions of nuclear norm minimization for low-rank matrix recovery. We obtain sufficient conditions δ_tr<t/(4-t) with 0<t<4/3 to guarantee the robust reconstruction (z≠0) or exact reconstruction (z=0) of all rank r matrices X∈R^m× n from b=A(X)+z via nuclear norm minimization. Furthermore, we not only show that when t=1, the upper bound of δ_r<1/3 is the same as the result of Cai and Zhang <cit.>, but also demonstrate that the gained upper bounds concerning the recovery error are better. Moreover, we prove that the restricted isometry property condition is sharp. Besides, the numerical experiments are conducted to reveal the nuclear norm minimization method is stable and robust for the recovery of low-rank matrix.



There are no comments yet.


page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.