{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "Courant Institute of Mathematical Sciences New York University New York City New York USA",
    "CIMS - Courant Institute of Mathematical Sciences [New York] (251, Mercier Street, New York, NY 10012 - United States)",
    "UMPA-ENSL - Unité de Mathématiques Pures et Appliquées (France)",
    "Unité de Mathématiques Pures et Appliquées (UMPA) ENS Lyon Lyon France"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Gérard Ben Arous",
      "orcid": "0000-0001-5599-8726"
    },
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Cédric Gerbelot"
    },
    {
      "affs": [
        3,
        2
      ],
      "name": "Vanessa Piccolo",
      "orcid": "0000-0003-0792-9798"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/epkwzzhxtm50t.bib",
  "cited_by": 12,
  "doi": "10.1002/cpa.70056",
  "fulltext_url": null,
  "id": "epkwzzhxtm50t",
  "issns": [
    "0010-3640",
    "1097-0312"
  ],
  "landing_url": "https://doi.org/10.1002/cpa.70056",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2605|Tensor decomposition and applications"
    ]
  ],
  "openalex": "W4404306248",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-24",
  "publisher": "Wiley",
  "ris": "https://research.draconitic.com/paper/epkwzzhxtm50t.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T13:20:36Z",
      "native_id": "W4404306248",
      "source": "openalex",
      "url": "https://doi.org/10.1002/cpa.70056"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "openalex:2605|Tensor decomposition and applications",
      "subfield": "numerical-analysis"
    }
  ],
  "title": "Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA",
  "title_text": "Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:00Z",
  "url": "https://research.draconitic.com/paper/epkwzzhxtm50t",
  "venue": "Communications on Pure and Applied Mathematics",
  "versions": []
}