Všechny publikace

Hoeffding–Serfling Inequality for U-Statistics Without Replacement

  • DOI: 10.1007/s10959-022-01169-x
  • Odkaz: https://doi.org/10.1007/s10959-022-01169-x
  • Pracoviště: Katedra počítačů, Intelligent Data Analysis
  • Anotace:
    Concentration inequalities quantify random fluctuations of functions of random variables, typically by bounding the probability that such a function differs from its expected value by more than a certain amount. In this paper we study one particular concentration inequality, the Hoeffding–Serfling inequality for U-statistics of random variables sampled without replacement from a finite set and extend recent results of Bardenet and Maillard (Bernoulli 21(3):1361–1385, 2015) to cover the U-statistics setting.

Hoeffding and Bernstein Inequalities for U-statistics without Replacement

  • DOI: 10.1016/j.spl.2022.109528
  • Odkaz: https://doi.org/10.1016/j.spl.2022.109528
  • Pracoviště: Katedra počítačů, Intelligent Data Analysis
  • Anotace:
    Concentration inequalities quantify random fluctuations of functions of random variables, typically by bounding the probability that such a function differs from its expected value by more than a certain amount. In this paper, we extend Hoeffding’s inequality and Bernstein’s inequality for U-statistics to the setting of sampling without replacement from a finite population.

Za stránku zodpovídá: Ing. Mgr. Radovan Suk