Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA
Communications on Pure and Applied Mathematics · 2026-10 · 79 (10) · 2291-2369
DOI: 10.1002/cpa.70056 ↗Kurz gefasst
Fachartikel in der Zeitschrift Communications on Pure and Applied Mathematics, online erschienen am 24.06.2026. Verfasst von Gérard Ben Arous und 2 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, European Research Council.
Abstract (Originalsprache)
We study the high‐dimensional dynamics of online stochastic gradient descent (SGD) for the multi‐spiked tensor model. This multi‐index model arises from the tensor principal component analysis (PCA) problem with multiple spikes, where the goal is to estimate the unknown signal vectors within the ‐dimensional unit sphere through maximum likelihood estimation from noisy observations of a ‐tensor. We determine the number of samples and the conditions on the signal‐to‐noise ratios (SNRs) required to efficiently recover the unknown spikes from natural random initializations. We show that full recovery of all spikes is possible provided a number of sample scaling as , matching the algorithmic threshold identified in the rank‐one case. Our results are obtained through a detailed analysis of a low‐dimensional system that describes the evolution of the correlations between the estimators and the spikes, while sharply controlling the noise in the dynamics. We find the spikes are recovered sequentially in a process we term “sequential elimination”: once a correlation exceeds a critical threshold, all correlations sharing a row or column index become sufficiently small, allowing the next correlation to grow and become macroscopic. The order in which correlations become macroscopic depends on their initial values and the corresponding SNRs, leading to either exact recovery or recovery of a permutation of the spikes. In the matrix case, when , if the SNRs are sufficiently separated, we achieve exact recovery of the spikes, whereas equal SNRs lead to recovery of the subspace spanned by them.
Förderung
- National Science Foundation
- European Research Council
Zitieren
APA
Arous, G. B., Gerbelot, C., & Piccolo, V. (2026). Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA. Communications on Pure and Applied Mathematics, 79(10), 2291-2369. https://doi.org/10.1002/cpa.70056
Vancouver
Arous GB, Gerbelot C, Piccolo V. Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA. Communications on Pure and Applied Mathematics. 2026;79(10):2291-2369. doi:10.1002/cpa.70056
BibTeX
@article{Arous2026,
author = {Arous, Gérard Ben and Gerbelot, Cédric and Piccolo, Vanessa},
title = {Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA},
journal = {Communications on Pure and Applied Mathematics},
year = {2026},
volume = {79},
number = {10},
pages = {2291--2369},
doi = {10.1002/cpa.70056}
}
EUVIMED