Spiked Singular Values and Vectors under Extreme Aspect Ratios

04/30/2021
by   Michael J. Feldman, et al.
0

The behavior of the leading singular values and vectors of noisy low-rank matrices is fundamental to many statistical and scientific problems. Theoretical understanding currently derives from asymptotic analysis under one of two regimes: classical, with a fixed number of rows, large number of columns or vice versa; and proportional, with large numbers of rows and columns, proportional to one another. This paper is concerned with the disproportional regime, where the matrix is either `tall and narrow' or `short and wide': we study sequences of matrices of size n × m_n with aspect ratio n/m_n → 0 or n/m_n →∞ as n →∞. This regime has important `big data' applications. Theory derived here shows that the displacement of the empirical singular values and vectors from their noise-free counterparts and the associated phase transitions – well-known under proportional growth asymptotics – still occur in the disproportionate setting. They must be quantified, however, on a novel scale of measurement that adjusts with the changing aspect ratio as the matrix size increases. In this setting, the top singular vectors corresponding to the longer of the two matrix dimensions are asymptotically uncorrelated with the noise-free signal.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/19/2021

Long Random Matrices and Tensor Unfolding

In this paper, we consider the singular values and singular vectors of l...
09/27/2018

Singular vector and singular subspace distribution for the matrix denoising model

In this paper, we study the matrix denosing model Y=S+X, where S is a lo...
12/23/2021

When Random Tensors meet Random Matrices

Relying on random matrix theory (RMT), this paper studies asymmetric ord...
01/16/2019

Optimal cleaning for singular values of cross-covariance matrices

We give a new algorithm for the estimation of the cross-covariance matri...
11/04/2014

A random algorithm for low-rank decomposition of large-scale matrices with missing entries

A Random SubMatrix method (RSM) is proposed to calculate the low-rank de...
03/24/2021

On the ℓ^∞-norms of the Singular Vectors of Arbitrary Powers of a Difference Matrix with Applications to Sigma-Delta Quantization

Let A _max := max_i,j |A_i,j| denote the maximum magnitude of entries of...
02/05/2018

On singular value distribution of large dimensional data matrices whose columns have different correlations

Suppose Y_n=( y_1,..., y_n) is a p× n data matrix whose columns y_j, 1...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.