Analysis of singular subspaces under random perturbations

2024/03/14 by Wang, Ke
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Numerical Analysis (math.NA) #Probability (math.PR) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2403.09170

Abstract

We present a comprehensive analysis of singular vector and singular subspace perturbations in the context of the signal plus random Gaussian noise matrix model. Assuming a low-rank signal matrix, we extend the Davis-Kahan-Wedin theorem in a fully generalized manner, applicable to any unitarily invariant matrix norm, extending previous results of O'Rourke, Vu and the author. We also obtain the fine-grained results, which encompass the ℓ_∞ analysis of singular vectors, the ℓ_{2, ∞} analysis of singular subspaces, as well as the exploration of linear and bilinear functions related to the singular vectors. Moreover, we explore the practical implications of these findings, in the context of the Gaussian mixture model and the submatrix localization problem.

Related

• Matrices with Gaussian noise: optimal estimates for singular subspace perturbation
• Singular vectors under random perturbation
• Singular Vector Perturbation under Gaussian Noise
• Singular vector and singular subspace distribution for the matrix denoising model
• Extreme value theory for singular subspace estimation in the matrix denoising model