English

A vector-contraction inequality for Rademacher complexities

Machine Learning 2016-05-04 v1 Machine Learning

Abstract

The contraction inequality for Rademacher averages is extended to Lipschitz functions with vector-valued domains, and it is also shown that in the bounding expression the Rademacher variables can be replaced by arbitrary iid symmetric and sub-gaussian variables. Example applications are given for multi-category learning, K-means clustering and learning-to-learn.

Keywords

Cite

@article{arxiv.1605.00251,
  title  = {A vector-contraction inequality for Rademacher complexities},
  author = {Andreas Maurer},
  journal= {arXiv preprint arXiv:1605.00251},
  year   = {2016}
}
R2 v1 2026-06-22T13:45:46.412Z