Journal article · 2026 · Open access

Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA

Gérard Ben Arous, Cédric Gerbelot, Vanessa Piccolo

Communications on Pure and Applied Mathematics, 79(10), 2291–2369 · Published 24 June 2026 · DOI 10.1002/cpa.70056

Open full textCite this paper

In brief

“Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA” is a 2026 journal article by Gérard Ben Arous and 2 co-authors, published in Communications on Pure and Applied Mathematics. OpenAlex counts 14 citations as of 17 November 2026, which puts it in the top 3% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Communications on Pure and Applied Mathematics.

Citations
14
Most cited in
2026 (9)
Field-weighted impact
8.74
References
65
Authors
3

Abstract

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

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

MLA 9

Arous, Gérard Ben, et al. “Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA.” Communications on Pure and Applied Mathematics, vol. 79, no. 10, 2026, pp. 2291–2369. https://doi.org/10.1002/cpa.70056.

Chicago

Arous, Gérard Ben, Cédric Gerbelot, and Vanessa Piccolo. 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.

Harvard

Arous, G. B., Gerbelot, C. and Piccolo, V. (2026) ‘Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA’, Communications on Pure and Applied Mathematics, 79(10), pp. 2291–2369. doi:10.1002/cpa.70056.

IEEE

G. B. Arous, C. Gerbelot, and V. Piccolo, “Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA,” Communications on Pure and Applied Mathematics, vol. 79, no. 10, pp. 2291–2369, 2026, doi: 10.1002/cpa.70056.

BibTeX

@article{arous2026stochastic,
  title     = {{Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA}},
  author    = {Arous, Gérard Ben and Gerbelot, Cédric and Piccolo, Vanessa},
  journal   = {Communications on Pure and Applied Mathematics},
  year      = {2026},
  volume    = {79},
  number    = {10},
  pages     = {2291--2369},
  doi       = {10.1002/cpa.70056},
  url       = {https://doi.org/10.1002/cpa.70056}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Mathematics › Computational Mathematics › Tensor decomposition and applications

  • stochastic gradient descent
  • high-dimensional statistics
  • tensor principal component analysis
  • signal-to-noise ratio
  • exact recovery
  • sequential elimination
  • low-dimensional dynamics
  • maximum likelihood estimation

Work with this paper

Most-cited papers in Mathematics

All highly cited Mathematics papers

Questions about this paper

How do I cite this paper in APA style?

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

How many times has this paper been cited?

14 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Communications on Pure and Applied Mathematics: sign in and open the full text from this page.

Who wrote this paper?

Gérard Ben Arous, Cédric Gerbelot, Vanessa Piccolo.

What is the DOI of this paper?

10.1002/cpa.70056, permanently at https://doi.org/10.1002/cpa.70056. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.