A Chain Rule for the Expected Suprema of Gaussian Processes

ALT 2014 pp. 245-259

doi:10.1007/978-3-319-11662-4_18 /alt/2014/maurer2014alt-chain/

Abstract

The expected supremum of a Gaussian process indexed by the image of an index set under a function class is bounded in terms of separate properties of the index set and the function class. The bound is relevant to the estimation of nonlinear transformations or the analysis of learning algorithms whenever hypotheses are chosen from composite classes, as is the case for multi-layer models.

PDF ALT Semantic Scholar

Cite

Text

Maurer. "A Chain Rule for the Expected Suprema of Gaussian Processes." International Conference on Algorithmic Learning Theory, 2014. doi:10.1007/978-3-319-11662-4_18

Markdown

[Maurer. "A Chain Rule for the Expected Suprema of Gaussian Processes." International Conference on Algorithmic Learning Theory, 2014.](https://mlanthology.org/alt/2014/maurer2014alt-chain/) doi:10.1007/978-3-319-11662-4_18

BibTeX

@inproceedings{maurer2014alt-chain,
  title     = {{A Chain Rule for the Expected Suprema of Gaussian Processes}},
  author    = {Maurer, Andreas},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2014},
  pages     = {245-259},
  doi       = {10.1007/978-3-319-11662-4_18},
  url       = {https://mlanthology.org/alt/2014/maurer2014alt-chain/}
}