Accession Number:

AD1105755

Title:

Sharp Restricted Isometry Bounds for the Inexistence ofSpurious Local Minima in Nonconvex Matrix Recovery

Descriptive Note:

Journal Article - Open Access

Corporate Author:

University of Illinois at Urbana-Champaign Urbana United States

Report Date:

2019-06-01

Pagination or Media Count:

34.0

Abstract:

Nonconvex matrix recovery is known to contain no spurious local minima under a restricted isometry property RIP with a sufficiently small RIP constant delta. If delta is too large, however, then counterexamples containing spurious local minima are known to exist. In this paper, we introduce a proof technique that is capable of establishing sharp thresholds on delta to guarantee the inexistence of spurious local minima.

Subject Categories:

  • Operations Research
  • Operations Research

Distribution Statement:

APPROVED FOR PUBLIC RELEASE