A1091
Title: Deep learning of multivariate extremes via a geometric representation
Authors: Callum Murphy-Barltrop - Technische Universitat Dresden (Germany) [presenting]
Abstract: Geometric representations for multivariate extremes, derived from the shapes of scaled sample clouds and their so-called limit sets, are becoming an increasingly popular modelling tool. Recent work has shown that limit sets connect several existing extremal dependence concepts and offer a high degree of practical utility for the inference of multivariate extremes. However, existing geometric approaches are limited to low-dimensional settings, and some of these techniques make strong assumptions about the form of the limit set. The purpose is to introduce DeepGauge - the first deep learning approach for limit set estimation. By leveraging the predictive power and computational scalability of neural networks, asymptotically-justified yet highly flexible semi-parametric models are constructed for extremal dependence. Unlike existing techniques, DeepGauge can be applied in high-dimensional settings and requires few assumptions. Moreover, a range of novel theoretical results are also introduced pertaining to the geometric framework and the limit set estimator. The efficacy of the deep approach is showcased by modelling the complex extremal dependence between metocean variables sampled from the North Sea.
