Long Random Matrices and Tensor Unfolding

10/19/2021
by   Gérard Ben Arous, et al.
4

In this paper, we consider the singular values and singular vectors of low rank perturbations of large rectangular random matrices, in the regime the matrix is "long": we allow the number of rows (columns) to grow polynomially in the number of columns (rows). We prove there exists a critical signal-to-noise ratio (depending on the dimensions of the matrix), and the extreme singular values and singular vectors exhibit a BBP type phase transition. As a main application, we investigate the tensor unfolding algorithm for the asymmetric rank-one spiked tensor model, and obtain an exact threshold, which is independent of the procedure of tensor unfolding. If the signal-to-noise ratio is above the threshold, tensor unfolding detects the signals; otherwise, it fails to capture the signals.

READ FULL TEXT
research
11/16/2022

On the Accuracy of Hotelling-Type Tensor Deflation: A Random Tensor Analysis

Leveraging on recent advances in random tensor theory, we consider in th...
research
04/30/2021

Spiked Singular Values and Vectors under Extreme Aspect Ratios

The behavior of the leading singular values and vectors of noisy low-ran...
research
06/06/2023

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression

In this paper we compare and contrast the behavior of the posterior pred...
research
12/05/2017

Phase transition in the spiked random tensor with Rademacher prior

We consider the problem of detecting a deformation from a symmetric Gaus...
research
12/23/2021

When Random Tensors meet Random Matrices

Relying on random matrix theory (RMT), this paper studies asymmetric ord...
research
12/22/2016

Statistical limits of spiked tensor models

We study the statistical limits of both detecting and estimating a rank-...
research
11/06/2018

Optimal singular value shrinkage with noise homogenization

We derive the optimal singular values for prediction in the spiked model...

Please sign up or login with your details

Forgot password? Click here to reset