Saved in:
Bibliographic Details
Main Authors: Lebeau, Hugo, Chatelain, Florent, Couillet, Romain
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.03169
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916566018293760
author Lebeau, Hugo
Chatelain, Florent
Couillet, Romain
author_facet Lebeau, Hugo
Chatelain, Florent
Couillet, Romain
contents This work presents a comprehensive understanding of the estimation of a planted low-rank signal from a general spiked tensor model near the computational threshold. Relying on standard tools from the theory of large random matrices, we characterize the large-dimensional spectral behavior of the unfoldings of the data tensor and exhibit relevant signal-to-noise ratios governing the detectability of the principal directions of the signal. These results allow to accurately predict the reconstruction performance of truncated multilinear SVD (MLSVD) in the non-trivial regime. This is particularly important since it serves as an initialization of the higher-order orthogonal iteration (HOOI) scheme, whose convergence to the best low-multilinear-rank approximation depends entirely on its initialization. We give a sufficient condition for the convergence of HOOI and show that the number of iterations before convergence tends to $1$ in the large-dimensional limit.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03169
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation
Lebeau, Hugo
Chatelain, Florent
Couillet, Romain
Machine Learning
Probability
This work presents a comprehensive understanding of the estimation of a planted low-rank signal from a general spiked tensor model near the computational threshold. Relying on standard tools from the theory of large random matrices, we characterize the large-dimensional spectral behavior of the unfoldings of the data tensor and exhibit relevant signal-to-noise ratios governing the detectability of the principal directions of the signal. These results allow to accurately predict the reconstruction performance of truncated multilinear SVD (MLSVD) in the non-trivial regime. This is particularly important since it serves as an initialization of the higher-order orthogonal iteration (HOOI) scheme, whose convergence to the best low-multilinear-rank approximation depends entirely on its initialization. We give a sufficient condition for the convergence of HOOI and show that the number of iterations before convergence tends to $1$ in the large-dimensional limit.
title A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation
topic Machine Learning
Probability
url https://arxiv.org/abs/2402.03169