Preprint · 2020 · Open access

Power Iteration for Tensor PCA

Jiaoyang Huang, Daniel Zhengyu Huang, Qing Yang, Guang Cheng

arXiv (Cornell University) · Published 26 December 2020 · DOI 10.48550/arxiv.2012.13669

Open PDFView at the publisherCite this paper

In brief

“Power Iteration for Tensor PCA” is a 2020 preprint by Jiaoyang Huang and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 13 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
13
Most cited in
2022 (5)
References
56
Authors
4

Abstract

In this paper, we study the power iteration algorithm for the spiked tensor model, as introduced in [44]. We give necessary and sufficient conditions for the convergence of the power iteration algorithm. When the power iteration algorithm converges, for the rank one spiked tensor model, we show the estimators for the spike strength and linear functionals of the signal are asymptotically Gaussian; for the multi-rank spiked tensor model, we show the estimators are asymptotically mixtures of Gaussian. This new phenomenon is different from the spiked matrix model. Using these asymptotic results of our estimators, we construct valid and efficient confidence intervals for spike strengths and linear functionals of the signals.

Cite this paper

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

APA 7

Huang, J., Huang, D. Z., Yang, Q., & Cheng, G. (2020). Power Iteration for Tensor PCA. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2012.13669

MLA 9

Huang, Jiaoyang, et al. “Power Iteration for Tensor PCA.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2012.13669.

Chicago

Huang, Jiaoyang, Daniel Zhengyu Huang, Qing Yang, and Guang Cheng. 2020. “Power Iteration for Tensor PCA.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2012.13669.

Harvard

Huang, J. et al. (2020) ‘Power Iteration for Tensor PCA’, arXiv (Cornell University). doi:10.48550/arxiv.2012.13669.

IEEE

J. Huang, D. Z. Huang, Q. Yang, and G. Cheng, “Power Iteration for Tensor PCA,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2012.13669.

BibTeX

@misc{huang2020power,
  title     = {{Power Iteration for Tensor PCA}},
  author    = {Huang, Jiaoyang and Huang, Daniel Zhengyu and Yang, Qing and Cheng, Guang},
  howpublished = {arXiv (Cornell University)},
  year      = {2020},
  doi       = {10.48550/arxiv.2012.13669},
  url       = {https://doi.org/10.48550/arxiv.2012.13669}
}

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

Citations by year

YearCitationsShare of the best year
202111
202255
202322
202411
202522
202622

Topic and keywords

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

  • power iteration
  • convergence conditions
  • asymptotic Gaussianity
  • confidence intervals
  • high-dimensional statistics

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?

Huang, J., Huang, D. Z., Yang, Q., & Cheng, G. (2020). Power Iteration for Tensor PCA. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2012.13669

How many times has this paper been cited?

13 times, according to OpenAlex on 18 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Jiaoyang Huang, Daniel Zhengyu Huang, Qing Yang, Guang Cheng.

What is the DOI of this paper?

10.48550/arxiv.2012.13669, permanently at https://doi.org/10.48550/arxiv.2012.13669. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.