2019

Efron-Stein PAC-Bayesian Inequalities

Kuzborskij, Ilja, Szepesvári, Csaba

Understand

We prove semi-empirical concentration inequalities for random variables which are given as possibly nonlinear functions of independent random variables.

  • These inequalities describe concentration of random variable in terms of the data/distribution-dependent Efron-Stein (ES) estimate of its variance and they do not require any additional assumptions on the moments.
  • In particular, this allows us to state semi-empirical Bernstein type inequalities for general functions of unbounded random variables, which gives user-friendly concentration bounds for cases where related methods (e.g.
  • bounded differences) might be more challenging to apply.

Reading the bibliography…