Entrywise Estimation of Singular Vectors of Low-Rank Matrices With Heteroskedasticity and Dependence-Reference-Cited by-同舟云学术

Entrywise Estimation of Singular Vectors of Low-Rank Matrices With Heteroskedasticity and Dependence

Published:2022-07 Issue:7 Volume:68 Page:4618-4650
ISSN:0018-9448
Container-title:IEEE Transactions on Information Theory
language:
Short-container-title:IEEE Trans. Inform. Theory

Author:

Agterberg Joshua¹^ORCID,Lubberts Zachary²^ORCID,Priebe Carey E.³^ORCID

Affiliation:

1. Department of Applied Mathematics and Statistics and the Mathematical Institute of Data Science, Johns Hopkins University, Baltimore, MD, USA

2. Human Language Technology Center of Excellence and the Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA

3. Center for Imaging Science, the Department of Applied Mathematics and Statistics, Mathematical Institute of Data Science, Johns Hopkins University, Baltimore, MD, USA

Funder

Fellowship from the Johns Hopkins Mathematical Institute of Data Science (MINDS) via its NSF Transdisciplinary Research in Principles of Data Science

Charles and Catherine Counselman Fellowship

Defense Advanced Research Projects Agency (DARPA) Data-Driven Discovery of Models

Naval Engineering Education Consortium

Office of Naval Research

Microsoft Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Library and Information Sciences,Computer Science Applications,Information Systems

Link

https://ieeexplore.ieee.org/ielam/18/9798707/9733353-aam.pdf

Reference76 articles.

1. Simultaneous dimensionality and complexity model selection for spectral graph clustering;yang;J Comput Graph Statist,2020

2. Universal rank inference via residual subsampling with application to large networks;han;arXiv 1912 11583,2019

3. Automatic dimensionality selection from the scree plot via the use of profile likelihood

4. Inference for heteroskedastic PCA with missing data;yan;arXiv 2107 12365,2021

5. Hanson–Wright inequality in Hilbert spaces with application to $K$-means clustering for non-Euclidean data

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Inference for heteroskedastic PCA with missing data;The Annals of Statistics;2024-04-01

2. Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals;Bernoulli;2024-02-01

3. An eigenvector-assisted estimation framework for signal-plus-noise matrix models;Biometrika;2023-09-19

4. Euclidean Representation of Low-Rank Matrices and Its Geometric Properties;SIAM Journal on Matrix Analysis and Applications;2023-06-06

5. Matrix denoising with partial noise statistics: optimal singular value shrinkage of spiked F-matrices;Information and Inference: A Journal of the IMA;2023-04-27