Concentration of the frobenius norm of generalized matrix inverses

Ivan Dokmanic, Remi Gribonval

Research output: Contribution to journalArticlepeer-review


In many applications it is useful to replace the Moore-Penrose pseudoinverse (MPP) by a different generalized inverse with more favorable properties. We may want, for example, to have many zero entries, but without giving up too much of the stability of the MPP. One way to quantify stability is by how much the Frobenius norm of a generalized inverse exceeds that of the MPP. In this paper we derive finite-size concentration bounds for the Frobenius norm of \ell p-minimal general inverses of iid Gaussian matrices, with 1 \le p \le 2. For p = 1 we prove exponential concentration of the Frobenius norm of the sparse pseudoinverse; for p = 2, we get a similar concentration bound for the MPP. Our proof is based on the convex Gaussian min-max theorem, but unlike previous applications which give asymptotic results, we derive finite-size bounds.

Original languageEnglish (US)
Pages (from-to)92-121
Number of pages30
JournalSIAM Journal on Matrix Analysis and Applications
Issue number1
StatePublished - 2019


  • Concentration bound
  • Convex analysis
  • Frobenius norm
  • Random matrices
  • Sparse pseudoinverse
  • \ell p minimization

ASJC Scopus subject areas

  • Analysis


Dive into the research topics of 'Concentration of the frobenius norm of generalized matrix inverses'. Together they form a unique fingerprint.

Cite this