Principal component analysis for multivariate extremes

DOI10.1214/21-EJS1803zbMath1498.62097arXiv1906.11043OpenAlexW3139230172MaRDI QIDQ2044326

Anne Sabourin, Holger Drees

Publication date: 9 August 2021

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.11043

zbMATH Keywords

principal component analysisdimension reductionempirical risk minimizationmultivariate regular variationmultivariate extreme value analysis

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Order statistics; empirical distribution functions (62G30) Extreme value theory; extremal stochastic processes (60G70) Statistics of extreme values; tail inference (62G32)

Related Items (5)

Total positivity in multivariate extremes ⋮ Tail inverse regression: dimension reduction for prediction of extremes ⋮ Simulating flood event sets using extremal principal components ⋮ Sparse regular variation ⋮ Extreme partial least-squares

Cites Work

• Unnamed Item
• Unnamed Item
• Regularly varying measures on metric spaces: hidden regular variation and hidden jumps
• The generalized Pareto process; with a view towards application and simulation
• Rank-based inference for bivariate extreme-value copulas
• Models for stationary max-stable random fields
• New asymptotic results in principal component analysis
• Robust bounds in multivariate extremes
• Multivariate generalized Pareto distributions: parametrizations, representations, and properties
• Tail dimension reduction for extreme quantile estimation
• Nonparametric estimation of the spectral measure of an extreme value distribution.
• Simulating multivariate extreme value distributions of logistic type
• Random matrix approximation of spectra of integral operators
• \(k\)-means clustering of extremes
• Nonasymptotic upper bounds for the reconstruction error of PCA
• Dimension reduction in multivariate extreme value analysis
• Identifying groups of variables with the potential of being large simultaneously
• Bias correction in multivariate extremes
• Sparse representation of multivariate extremes with applications to anomaly detection
• Max-stable models for multivariate extremes
• Regular variation for measures on metric spaces
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• Asymptotic Statistics
• Learning Theory
• Determining the dependence structure of multivariate extremes
• Likelihood-Based Inference for Max-Stable Processes
• Probability Inequalities for Sums of Bounded Random Variables
• Heavy-Tail Phenomena
• Asymptotic Theory for Principal Component Analysis
• Decompositions of dependence for high-dimensional extremes

This page was built for publication: Principal component analysis for multivariate extremes