Principal Component Analysis for Multivariate Extremes
This work addresses dimension reduction for extreme value analysis in high-dimensional data, which is incremental as it adapts PCA to a specific statistical framework for heavy-tailed distributions.
The paper tackles the problem of identifying a lower-dimensional subspace for multivariate heavy-tailed data above large thresholds by applying Principal Component Analysis to rescaled thresholded observations, proving convergence of the empirical risk to the true risk and showing that the estimated subspace converges to the optimal one with finite sample guarantees.
The first order behavior of multivariate heavy-tailed random vectors above large radial thresholds is ruled by a limit measure in a regular variation framework. For a high dimensional vector, a reasonable assumption is that the support of this measure is concentrated on a lower dimensional subspace, meaning that certain linear combinations of the components are much likelier to be large than others. Identifying this subspace and thus reducing the dimension will facilitate a refined statistical analysis. In this work we apply Principal Component Analysis (PCA) to a re-scaled version of radially thresholded observations. Within the statistical learning framework of empirical risk minimization, our main focus is to analyze the squared reconstruction error for the exceedances over large radial thresholds. We prove that the empirical risk converges to the true risk, uniformly over all projection subspaces. As a consequence, the best projection subspace is shown to converge in probability to the optimal one, in terms of the Hausdorff distance between their intersections with the unit sphere. In addition, if the exceedances are re-scaled to the unit ball, we obtain finite sample uniform guarantees to the reconstruction error pertaining to the estimated projection sub-space. Numerical experiments illustrate the relevance of the proposed framework for practical purposes.