A Perturbation Bound on the Subspace Estimator from Canonical Projections

2022/06/28 by Karan Srivastava, Srivastava, Karan, Daniel Pimentel-Alarcón +1
Computer Science · Engineering · Mathematics · #Direction-of-Arrival Estimation Techniques #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Sparse and Compressive Sensing Techniques #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.2206.14278

openalex publication_date 2022/06/28 · openalex created_date 2022/07/02 · openalex updated_date 2026/07/28

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.

Related

• Van Trees inequality, group equivariance, and estimation of principal subspaces
• Rate-Optimal Perturbation Bounds for Singular Subspaces with Applications to High-Dimensional Statistics
• Matrix Perturbation: Davis-Kahan in the Infinity Norm
• Unperturbed: spectral analysis beyond Davis-Kahan
• A Schatten-q Low-rank Matrix Perturbation Analysis via Perturbation Projection Error Bound