Improved Rademacher symmetrization through a Wasserstein based measure of asymmetry
arXiv:1610.08405 · doi:10.1214/18-EJS1440
Abstract
We propose of an improved version of the ubiquitous symmetrization inequality making use of the Wasserstein distance between a measure and its reflection in order to quantify the symmetry of the given measure. An empirical bound on this asymmetric correction term is derived through a bootstrap procedure and shown to give tighter results in practical settings than the original uncorrected inequality. Lastly, a wide range of applications are detailed including testing for data symmetry, constructing nonasymptotic high dimensional confidence sets, bounding the variance of an empirical process, and improving constants in Nemirovski style inequalities for Banach space valued random variables.
arXiv comment15 pages, 3 figures
References in corpus (5)
- 2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization
- Global uniform risk bounds for wavelet deconvolution estimators
- Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
- Concentration Inequalities and Confidence Bands for Needlet Density Estimators on Compact Homogeneous Manifolds
- Inference on covariance operators via concentration inequalities: k-sample tests, classification, and clustering via Rademacher complexities