EUVIMEDEUVIMED entdecken
Crossref

Concentration bounds for the empirical angular measure with statistical learning applications

Stéphan Clémençon, Hamid Jalalzai, Stéphane Lhaut, Anne Sabourin, Johan Segers

Bernoulli · 01.11.2023 · 29 (4) · 2797-2827

DOI: 10.3150/22-bej1562 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bernoulli, erschienen am 01.11.2023. Verfasst von Stéphan Clémençon und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 54 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The angular measure on the unit sphere characterizes the first-order dependence structure of the components of a random vector in extreme regions and is defined in terms of standardized margins. Its statistical recovery is an important step in learning problems involving observations far away from the center. In the common situation that the components of the vector have different distributions, the rank transformation offers a convenient and robust way of standardizing data in order to build an empirical version of the angular measure based on the most extreme observations. However, the study of the sampling distribution of the resulting empirical angular measure is challenging. It is the purpose of the paper to establish finite-sample bounds for the maximal deviations between the empirical and true angular measures, uniformly over classes of Borel sets of controlled combinatorial complexity. The bounds are valid with high probability and, up to logarithmic factors, scale as the square root of the effective sample size. The bounds are applied to provide performance guarantees for two statistical learning procedures tailored to extreme regions of the input space and built upon the empirical angular measure: binary classification in extreme regions through empirical risk minimization and unsupervised anomaly detection through minimum-volume sets of the sphere.

Zitieren

APA

Clémençon, S., Jalalzai, H., Lhaut, S., Sabourin, A., & Segers, J. (2023). Concentration bounds for the empirical angular measure with statistical learning applications. Bernoulli, 29(4), 2797-2827. https://doi.org/10.3150/22-bej1562

Vancouver

Clémençon S, Jalalzai H, Lhaut S, Sabourin A, Segers J. Concentration bounds for the empirical angular measure with statistical learning applications. Bernoulli. 2023;29(4):2797-2827. doi:10.3150/22-bej1562

BibTeX
@article{Clmenon2023,
  author = {Clémençon, Stéphan and Jalalzai, Hamid and Lhaut, Stéphane and Sabourin, Anne and Segers, Johan},
  title = {Concentration bounds for the empirical angular measure with statistical learning applications},
  journal = {Bernoulli},
  year = {2023},
  volume = {29},
  number = {4},
  pages = {2797--2827},
  doi = {10.3150/22-bej1562}
}
Kostenlos starten →