ML Anthology

The Rademacher Complexity of Linear Transformation Classes

Andreas Maurer
COLT 2006 pp. 65-78
doi:10.1007/11776420_8 /colt/2006/maurer2006colt-rademacher/

Abstract

Bounds are given for the empirical and expected Rademacher complexity of classes of linear transformations from a Hilbert space H to a finite dimensional space. The results imply generalization guarantees for graph regularization and multi-task subspace learning.

PDF COLT Semantic Scholar

Cite

Text

Maurer. "The Rademacher Complexity of Linear Transformation Classes." Annual Conference on Computational Learning Theory, 2006. doi:10.1007/11776420_8

Markdown

[Maurer. "The Rademacher Complexity of Linear Transformation Classes." Annual Conference on Computational Learning Theory, 2006.](https://mlanthology.org/colt/2006/maurer2006colt-rademacher/) doi:10.1007/11776420_8

BibTeX

@inproceedings{maurer2006colt-rademacher,
  title     = {{The Rademacher Complexity of Linear Transformation Classes}},
  author    = {Maurer, Andreas},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2006},
  pages     = {65-78},
  doi       = {10.1007/11776420_8},
  url       = {https://mlanthology.org/colt/2006/maurer2006colt-rademacher/}
}