Uniform concentration and symmetrization for weak interactions

02/05/2019
by   Andreas Maurer, et al.
0

The method to derive uniform bounds with Gaussian and Rademacher complexities is extended to the case where the sample average is replaced by a nonlinear statistic. Tight bounds are obtained for U-statistics, smoothened L-statistics and error functionals of l2-regularized algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2023

Another look at Stein's method for Studentized nonlinear statistics with an application to U-statistics

We take another look at using Stein's method to establish uniform Berry-...
research
03/11/2018

Empirical bounds for functions with weak interactions

We provide sharp empirical estimates of expectation, variance and normal...
research
06/29/2023

Poisson and Gaussian approximations of the power divergence family of statistics

Consider the family of power divergence statistics based on n trials, ea...
research
02/09/2022

An Exploration of Multicalibration Uniform Convergence Bounds

Recent works have investigated the sample complexity necessary for fair ...
research
05/21/2022

Smoothing Codes and Lattices: Systematic Study and New Bounds

In this article we revisit smoothing bounds in parallel between lattices...
research
11/25/2009

On ℓ_1-regularized estimation for nonlinear models that have sparse underlying linear structures

In a recent work (arXiv:0910.2517), for nonlinear models with sparse und...
research
03/15/2023

Nonuniform Berry-Esseen bounds for Studentized U-statistics

We establish nonuniform Berry-Esseen (B-E) bounds for Studentized U-stat...

Please sign up or login with your details

Forgot password? Click here to reset