ML Anthology

Stability of Unstable Learning Algorithms

Don R. Hush, Clint Scovel, Ingo Steinwart
MLJ 2007 pp. 197-206
doi:10.1007/S10994-007-5004-Z /mlj/2007/hush2007mlj-stability/

Abstract

We introduce graphical learning algorithms and use them to produce bounds on error deviance for unstable learning algorithms which possess a partial form of stability. As an application we obtain error deviance bounds for support vector machines (SVMs) with variable offset parameter.

PDF MLJ Semantic Scholar

Cite

Text

Hush et al. "Stability of Unstable Learning Algorithms." Machine Learning, 2007. doi:10.1007/S10994-007-5004-Z

Markdown

[Hush et al. "Stability of Unstable Learning Algorithms." Machine Learning, 2007.](https://mlanthology.org/mlj/2007/hush2007mlj-stability/) doi:10.1007/S10994-007-5004-Z

BibTeX

@article{hush2007mlj-stability,
  title     = {{Stability of Unstable Learning Algorithms}},
  author    = {Hush, Don R. and Scovel, Clint and Steinwart, Ingo},
  journal   = {Machine Learning},
  year      = {2007},
  pages     = {197-206},
  doi       = {10.1007/S10994-007-5004-Z},
  volume    = {67},
  url       = {https://mlanthology.org/mlj/2007/hush2007mlj-stability/}
}