Asymptotic sequential Rademacher complexity of a finite function class

05/11/2016

∙

by   Dmitry B. Rokhlin, et al.

∙

0

∙

share

For a finite function class we describe the large sample limit of the sequential Rademacher complexity in terms of the viscosity solution of a G-heat equation. In the language of Peng's sublinear expectation theory, the same quantity equals to the expected value of the largest order statistics of a multidimensional G-normal random variable. We illustrate this result by deriving upper and lower bounds for the asymptotic sequential Rademacher complexity.