A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation
Authors
Paper Information
-
Journal:
Journal of Machine Learning Research -
Added to Tracker:
Jul 15, 2025
Abstract
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.
Author Details
Hugo Lebeau
AuthorFlorent Chatelain
AuthorRomain Couillet
AuthorCitation Information
APA Format
Hugo Lebeau
,
Florent Chatelain
&
Romain Couillet
.
A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation.
Journal of Machine Learning Research
.
BibTeX Format
@article{JMLR:v26:24-0193,
author = {Hugo Lebeau and Florent Chatelain and Romain Couillet},
title = {A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation},
journal = {Journal of Machine Learning Research},
year = {2025},
volume = {26},
number = {7},
pages = {1--64},
url = {http://jmlr.org/papers/v26/24-0193.html}
}