High-dimensional rank-one nonsymmetric matrix decomposition: the spherical case

04/15/2020
by   Clément Luneau, et al.
0

We consider the problem of estimating a rank-one nonsymmetric matrix under additive white Gaussian noise. The matrix to estimate can be written as the outer product of two vectors and we look at the special case in which both vectors are uniformly distributed on spheres. We prove a replica-symmetric formula for the average mutual information between these vectors and the observations in the high-dimensional regime. This goes beyond previous results which considered vectors with independent and identically distributed elements. The method used can be extended to rank-one tensor problems.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

04/13/2018

On the detection of low rank matrices in the high-dimensional regime

We address the detection of a low rank n× ndeterministic matrix X_0 from...
04/09/2019

Mutual Information for Low-Rank Even-Order Symmetric Tensor Factorization

We consider a statistical model for finite-rank symmetric tensor factori...
11/19/2015

Spherical Cap Packing Asymptotics and Rank-Extreme Detection

We study the spherical cap packing problem with a probabilistic approach...
11/12/2019

0-1 phase transitions in sparse spiked matrix estimation

We consider statistical models of estimation of a rank-one matrix (the s...
06/25/2013

Fourier PCA and Robust Tensor Decomposition

Fourier PCA is Principal Component Analysis of a matrix obtained from hi...
06/24/2021

On the detection of low-rank signal in the presence of spatially uncorrelated noise: a frequency domain approach

This paper analyzes the detection of a M-dimensional useful signal model...
02/09/2019

Optimal Latent Representations: Distilling Mutual Information into Principal Pairs

Principal component analysis (PCA) is generalized from one to two random...
This week in AI

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