AISTATS 2019poster4 citations

Classification using margin pursuit

Matthew J. Holland

Abstract

In this work, we study a new approach to optimizing the margin distribution realized by binary classifiers, in which the learner searches the hypothesis space in such a way that a pre-set margin level ends up being a distribution-robust estimator of the margin location. This procedure is easily implemented using gradient descent, and admits finite-sample bounds on the excess risk under unbounded inputs, yielding competitive rates under mild assumptions. Empirical tests on real-world benchmark data reinforce the basic principles highlighted by the theory.

BibTeX
@InProceedings{pmlr-v89-holland19b,
  title = 	 {Classification using margin pursuit},
  author =       {Holland, Matthew J.},
  booktitle = 	 {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics},
  pages = 	 {712--720},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Sugiyama, Masashi},
  volume = 	 {89},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {16--18 Apr},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v89/holland19b/holland19b.pdf},
  url = 	 {https://proceedings.mlr.press/v89/holland19b.html},
  abstract = 	 {In this work, we study a new approach to optimizing the margin distribution realized by binary classifiers, in which the learner searches the hypothesis space in such a way that a pre-set margin level ends up being a distribution-robust estimator of the margin location. This procedure is easily implemented using gradient descent, and admits finite-sample bounds on the excess risk under unbounded inputs, yielding competitive rates under mild assumptions. Empirical tests on real-world benchmark data reinforce the basic principles highlighted by the theory.}
}
Classification using margin pursuit · AISTATS 2019