The Entropy Regularization Information Criterion

Abstract

Effective methods of capacity control via uniform convergence bounds for function expansions have been largely limited to Support Vector ma(cid:173) chines, where good bounds are obtainable by the entropy number ap(cid:173) proach. We extend these methods to systems with expansions in terms of arbitrary (parametrized) basis functions and a wide range of regulariza(cid:173) tion methods covering the whole range of general linear additive models. This is achieved by a data dependent analysis of the eigenvalues of the corresponding design matrix.

Cite

Text

Smola et al. "The Entropy Regularization Information Criterion." Neural Information Processing Systems, 1999.

Markdown

[Smola et al. "The Entropy Regularization Information Criterion." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/smola1999neurips-entropy/)

BibTeX

@inproceedings{smola1999neurips-entropy,
  title     = {{The Entropy Regularization Information Criterion}},
  author    = {Smola, Alex J. and Shawe-Taylor, John and Schölkopf, Bernhard and Williamson, Robert C.},
  booktitle = {Neural Information Processing Systems},
  year      = {1999},
  pages     = {342-348},
  url       = {https://mlanthology.org/neurips/1999/smola1999neurips-entropy/}
}