Empirical Bounds for Functions with Weak Interactions

Abstract

We provide sharp empirical estimates of expectation, variance and normal approximation for a class of statistics whose variation in any argument does not change too much when another argument is modified. Examples of such weak interactions are furnished by U- and V-statistics, Lipschitz L-statistics and various error functionals of L2-regularized algorithms and Gibbs algorithms.

Cite

Text

Maurer and Pontil. "Empirical Bounds for Functions with Weak Interactions." Annual Conference on Computational Learning Theory, 2018.

Markdown

[Maurer and Pontil. "Empirical Bounds for Functions with Weak Interactions." Annual Conference on Computational Learning Theory, 2018.](https://mlanthology.org/colt/2018/maurer2018colt-empirical/)

BibTeX

@inproceedings{maurer2018colt-empirical,
  title     = {{Empirical Bounds for Functions with Weak Interactions}},
  author    = {Maurer, Andreas and Pontil, Massimiliano},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2018},
  pages     = {987-1010},
  url       = {https://mlanthology.org/colt/2018/maurer2018colt-empirical/}
}