DeepAI AI Chat
Log In Sign Up

High-probability bounds for the reconstruction error of PCA

by   Cassandra Uebel, et al.
Humboldt-Universität zu Berlin

We identify principal component analysis (PCA) as an empirical risk minimization problem and prove error bounds that hold with high probability. More precisely, we derive upper bounds for the reconstruction error of PCA that can be expressed relative to the minimal reconstruction error. The significance of these bounds is shown for the cases of functional and kernel PCA. In such scenarios, the eigenvalues of the covariance operator often decay at a polynomial or nearly exponential rate. Our results yield that the reconstruction error of PCA achieves the same rate as the minimal reconstruction error.


page 1

page 2

page 3

page 4


Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms

Sparse Principal Component Analysis (PCA) is a prevalent tool across a p...

Upper and Lower Bounds on the Performance of Kernel PCA

Principal Component Analysis (PCA) is a popular method for dimension red...

A Communication-Efficient Distributed Algorithm for Kernel Principal Component Analysis

Principal Component Analysis (PCA) is a fundamental technology in machin...

An Analytical Formula for Spectrum Reconstruction

We study the spectrum reconstruction technique. As is known to all, eige...

Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm

We consider a family of vector dot products that can be implemented usin...

Principal Component Analysis for Multivariate Extremes

The first order behavior of multivariate heavy-tailed random vectors abo...