A Perturbation Bound on the Subspace Estimator from Canonical Projections

06/28/2022

∙

by   Karan Srivastava, et al.

∙

0

∙

share

This paper derives a perturbation bound on the optimal subspace estimator obtained from a subset of its canonical projections contaminated by noise. This fundamental result has important implications in matrix completion, subspace clustering, and related problems.