ML Anthology

Uniform Concentration and Symmetrization for Weak Interactions

Andreas Maurer, Massimiliano Pontil
COLT 2019 pp. 2372-2387
/colt/2019/maurer2019colt-uniform/

Abstract

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.

PDF COLT Semantic Scholar

Cite

Text

Maurer and Pontil. "Uniform Concentration and Symmetrization for Weak Interactions." Conference on Learning Theory, 2019.

Markdown

[Maurer and Pontil. "Uniform Concentration and Symmetrization for Weak Interactions." Conference on Learning Theory, 2019.](https://mlanthology.org/colt/2019/maurer2019colt-uniform/)

BibTeX

@inproceedings{maurer2019colt-uniform,
  title     = {{Uniform Concentration and Symmetrization for Weak Interactions}},
  author    = {Maurer, Andreas and Pontil, Massimiliano},
  booktitle = {Conference on Learning Theory},
  year      = {2019},
  pages     = {2372-2387},
  volume    = {99},
  url       = {https://mlanthology.org/colt/2019/maurer2019colt-uniform/}
}