A Perturbation Bound on the Subspace Estimator from Canonical Projections

Abstract

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.

Publication
IEEE International Symposium on Information Theory, 2022

You can find relevant code here. You can also find my ISIT 22 presentation slides on this paper here .

Karan Srivastava
Karan Srivastava
PhD Student, Mathematics

My research interests include machine learning, reinforcement learning, combinatorics, and algebraic geometry