Kernel PCA for multivariate extremes
Preprint
Abstract
We propose kernel PCA as a method for analyzing the dependence structure of multivariate extremes and demonstrate that it can be a powerful tool for clustering and dimension reduction. Our work provides some theoretical insight into the preimages obtained by kernel PCA, demonstrating that under certain conditions they can effectively identify clusters in the data. We build on these new insights to characterize rigorously the performance of kernel PCA based on an extremal sample, i.e., the angular part of random vectors for which the radius exceeds a large threshold. More specifically, we focus on the asymptotic dependence of multivariate extremes characterized by the angular or spectral measure in extreme value theory and provide a careful analysis in the case where the extremes are generated from a linear factor model. We give theoretical guarantees on the performance of kernel PCA preimages of such extremes by leveraging their asymptotic distribution together with Davis-Kahan perturbation bounds. Our theoretical findings are complemented with numerical experiments illustrating the finite sample performance of our methods.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Estimation and Inference of Extremal Quantile Treatment Effects for Heavy-Tailed DistributionsJournal of the American Statistical Association, 2023
- Spherical clustering in detection of groups of concomitant extremesBiometrika, 2022
- Sparse regular variationAdvances in Applied Probability, 2021
- Determining the dependence structure of multivariate extremesBiometrika, 2020
- Decompositions of dependence for high-dimensional extremesBiometrika, 2019
- Sparse representation of multivariate extremes with applications to anomaly detectionJournal of Multivariate Analysis, 2017
- A useful variant of the Davis–Kahan theorem for statisticiansBiometrika, 2014
- Statistical Properties of Kernel Principal Component Analysis2004
- Kernel PCA for Feature Extraction and De-Noising in Nonlinear RegressionNeural Computing and Applications, 2001
- Extreme Values, Regular Variation and Point Processes1987