A Geometric Analysis of PCA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hanchi, Ayoub El, Erdogdu, Murat, Maddison, Chris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908609122664448
author Hanchi, Ayoub El
Erdogdu, Murat
Maddison, Chris
author_facet Hanchi, Ayoub El
Erdogdu, Murat
Maddison, Chris
contents What property of the data distribution determines the excess risk of principal component analysis? In this paper, we provide a precise answer to this question. We establish a central limit theorem for the error of the principal subspace estimated by PCA, and derive the asymptotic distribution of its excess risk under the reconstruction loss. We obtain a non-asymptotic upper bound on the excess risk of PCA that recovers, in the large sample limit, our asymptotic characterization. Underlying our contributions is the following result: we prove that the negative block Rayleigh quotient, defined on the Grassmannian, is generalized self-concordant along geodesics emanating from its minimizer of maximum rotation less than $π/4$.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20978
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Geometric Analysis of PCA
Hanchi, Ayoub El
Erdogdu, Murat
Maddison, Chris
Statistics Theory
Machine Learning
What property of the data distribution determines the excess risk of principal component analysis? In this paper, we provide a precise answer to this question. We establish a central limit theorem for the error of the principal subspace estimated by PCA, and derive the asymptotic distribution of its excess risk under the reconstruction loss. We obtain a non-asymptotic upper bound on the excess risk of PCA that recovers, in the large sample limit, our asymptotic characterization. Underlying our contributions is the following result: we prove that the negative block Rayleigh quotient, defined on the Grassmannian, is generalized self-concordant along geodesics emanating from its minimizer of maximum rotation less than $π/4$.
title A Geometric Analysis of PCA
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2510.20978