DeepAI AI Chat
Log In Sign Up

Extremes in High Dimensions: Methods and Scalable Algorithms

by   Johannes Lederer, et al.
University of Stuttgart
Ruhr University Bochum

Extreme-value theory has been explored in considerable detail for univariate and low-dimensional observations, but the field is still in an early stage regarding high-dimensional multivariate observations. In this paper, we focus on Hüsler-Reiss models and their domain of attraction, a popular class of models for multivariate extremes that exhibit some similarities to multivariate Gaussian distributions. We devise novel estimators for the parameters of this model based on score matching and equip these estimators with state-of-the-art theories for high-dimensional settings and with exceptionally scalable algorithms. We perform a simulation study to demonstrate that the estimators can estimate a large number of parameters reliably and fast; for example, we show that Hüsler-Reiss models with thousands of parameters can be fitted within a couple of minutes on a standard laptop.


page 1

page 2

page 3

page 4


Asymptotic normality of generalized maximum spacing estimators for multivariate observations

In this paper, the maximum spacing method is considered for multivariate...

Score matching for compositional distributions

Compositional data and multivariate count data with known totals are cha...

Prediction regions through Inverse Regression

Predict a new response from a covariate is a challenging task in regress...

Estimating Barycenters of Measures in High Dimensions

Barycentric averaging is a principled way of summarizing populations of ...

Bayesian inference on high-dimensional multivariate binary data

It has become increasingly common to collect high-dimensional binary dat...

Exchangeable FGM copulas

Copulas are a powerful tool to model dependence between the components o...

Robust thin-plate splines for multivariate spatial smoothing

We propose a novel family of multivariate robust smoothers based on the ...