On the stability of bootstrap estimators
Statistics Theory
2011-11-09 v1 Machine Learning
Statistics Theory
Abstract
It is shown that bootstrap approximations of an estimator which is based on a continuous operator from the set of Borel probability measures defined on a compact metric space into a complete separable metric space is stable in the sense of qualitative robustness. Support vector machines based on shifted loss functions are treated as special cases.
Cite
@article{arxiv.1111.1876,
title = {On the stability of bootstrap estimators},
author = {Andreas Christmann and Matias Salibian-Barrera and Stefan Van Aelst},
journal= {arXiv preprint arXiv:1111.1876},
year = {2011}
}