Skip to Main content Skip to Navigation
Journal articles

Learning the dependence structure of rare events: a non-asymptotic study

Abstract : Assessing the probability of occurrence of extreme events is a crucial issue in various fields like finance, insurance, telecommunication or environmental sciences. In a multivariate framework, the tail dependence is characterized by the so-called stable tail dependence function (STDF). Learning this structure is the keystone of multivariate extremes. Although extensive studies have proved consistency and asymptotic normality for the empirical version of the STDF, non-asymptotic bounds are still missing. The main purpose of this paper is to fill this gap. Taking advantage of adapted VC-type concentration inequalities, upper bounds are derived with expected rate of convergence in O(k −1/2). The concentration tools involved in this analysis rely on a more general study of maximal deviations in low probability regions, and thus directly apply to the classification of extreme data.
Complete list of metadata

https://hal.telecom-paris.fr/hal-02107454
Contributor : Stephan Clémençon Connect in order to contact the contributor
Submitted on : Sunday, February 6, 2022 - 3:39:07 PM
Last modification on : Thursday, February 17, 2022 - 4:35:11 PM
Long-term archiving on: : Saturday, May 7, 2022 - 6:02:26 PM

File

Goix15.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-02107454, version 1

Collections

Citation

Nicolas Goix, Anne Sabourin, Stéphan Clémençon. Learning the dependence structure of rare events: a non-asymptotic study. JMLR: Workshop and Conference Proceedings, 2015, 40, pp.1 - 18. ⟨hal-02107454⟩

Share

Metrics

Record views

29

Files downloads

2