A Perturbation Bound on the Subspace Estimator from Canonical Projections

06/28/2022
by   Karan Srivastava, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2018

Random perturbation and matrix sparsification and completion

We discuss general perturbation inequalities when the perturbation is ra...
research
10/02/2014

Deterministic Conditions for Subspace Identifiability from Incomplete Sampling

Consider a generic r-dimensional subspace of R^d, r<d, and suppose that ...
research
08/04/2021

Gohberg-Kaashoek Numbers and Stability of the Schur Canonical Form

In the present paper, we characterize the stability of the Schur canonic...
research
10/19/2019

Robustifying multiple-set linear canonical analysis with S-estimator

We consider a robust version of multiple-set linear canonical analysis o...
research
05/09/2019

Projections onto the canonical simplex with additional linear inequalities

We consider projections onto the canonical simplex with additional linea...
research
03/30/2022

Near-Optimal Weighted Matrix Completion

Recent work in the matrix completion literature has shown that prior kno...
research
06/09/2020

Homomorphic Sensing of Subspace Arrangements

Homomorphic sensing is a recent algebraic-geometric framework that studi...

Please sign up or login with your details

Forgot password? Click here to reset