Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kumar, Syamantak, Pandey, Shourya, Sarkar, Purnamrita
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911065834520576
author Kumar, Syamantak
Pandey, Shourya
Sarkar, Purnamrita
author_facet Kumar, Syamantak
Pandey, Shourya
Sarkar, Purnamrita
contents We propose a novel statistical inference framework for streaming principal component analysis (PCA) using Oja's algorithm, enabling the construction of confidence intervals for individual entries of the estimated eigenvector. Most existing works on streaming PCA focus on providing sharp sin-squared error guarantees. Recently, there has been some interest in uncertainty quantification for the sin-squared error. However, uncertainty quantification or sharp error guarantees for entries of the estimated eigenvector in the streaming setting remains largely unexplored. We derive a sharp Bernstein-type concentration bound for elements of the estimated vector matching the optimal error rate up to logarithmic factors. We also establish a Central Limit Theorem for a suitably centered and scaled subset of the entries. To efficiently estimate the coordinate-wise variance, we introduce a provably consistent subsampling algorithm that leverages the median-of-means approach, empirically achieving similar accuracy to multiplier bootstrap methods while being significantly more computationally efficient. Numerical experiments demonstrate its effectiveness in providing reliable uncertainty estimates with a fraction of the computational cost of existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12655
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA
Kumar, Syamantak
Pandey, Shourya
Sarkar, Purnamrita
Statistics Theory
Machine Learning
We propose a novel statistical inference framework for streaming principal component analysis (PCA) using Oja's algorithm, enabling the construction of confidence intervals for individual entries of the estimated eigenvector. Most existing works on streaming PCA focus on providing sharp sin-squared error guarantees. Recently, there has been some interest in uncertainty quantification for the sin-squared error. However, uncertainty quantification or sharp error guarantees for entries of the estimated eigenvector in the streaming setting remains largely unexplored. We derive a sharp Bernstein-type concentration bound for elements of the estimated vector matching the optimal error rate up to logarithmic factors. We also establish a Central Limit Theorem for a suitably centered and scaled subset of the entries. To efficiently estimate the coordinate-wise variance, we introduce a provably consistent subsampling algorithm that leverages the median-of-means approach, empirically achieving similar accuracy to multiplier bootstrap methods while being significantly more computationally efficient. Numerical experiments demonstrate its effectiveness in providing reliable uncertainty estimates with a fraction of the computational cost of existing methods.
title Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2506.12655