The stability of low-rank matrix reconstruction: A constrained singular value view

  • Gongguo Tang
  • , Arye Nehorai

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

The stability of low-rank matrix reconstruction with respect to noise is investigated in this paper. The ℓ*-constrained minimal singular value (ℓ*-CMSV) of the measurement operator is shown to determine the recovery performance of nuclear norm minimization-based algorithms. Compared with the stability results using the matrix restricted isometry constant, the performance bounds established using ℓ*-CMSV are more concise, and their derivations are less complex. Isotropic and subgaussian measurement operators are shown to have ℓ*-CMSVs bounded away from zero with high probability, as long as the number of measurements is relatively large. The ℓ*-CMSV for correlated Gaussian operators are also analyzed and used to illustrate the advantage of ℓ*-CMSV compared with the matrix restricted isometry constant. We also provide a fixed point characterization of ℓ*-CMSV that is potentially useful for its computation.

Original languageEnglish
Article number6217312
Pages (from-to)6079-6092
Number of pages14
JournalIEEE Transactions on Information Theory
Volume58
Issue number9
DOIs
StatePublished - 2012

Keywords

  • correlated design
  • matrix Dantzig selector (mDS)
  • matrix LASSO estimator (mLASSO)
  • matrix basis pursuit (mBP)
  • restricted isometry property
  • ℓ*-constrained minimal singular value (CMSV)

Fingerprint

Dive into the research topics of 'The stability of low-rank matrix reconstruction: A constrained singular value view'. Together they form a unique fingerprint.

Cite this