Distance-Based Classification with Lipschitz Functions

@article{Luxburg2003DistanceBasedCW,
  title={Distance-Based Classification with Lipschitz Functions},
  author={Ulrike von Luxburg and Olivier Bousquet},
  journal={Journal of Machine Learning Research},
  year={2003},
  volume={5},
  pages={669-695}
}
The goal of this article is to develop a framework for large margin classification in metric spaces. We want to find a generalization of linear decision functions for metric spaces and define a corresponding notion of margin such that the decision function separates the training points with a large margin. It will turn out that using Lipschitz functions as decision functions, the inverse of the Lipschitz constant can be interpreted as the size of a margin. In order to construct a clean… CONTINUE READING
BETA

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.

153 Citations

051015'03'06'10'14'18
Citations per Year
Semantic Scholar estimates that this publication has 153 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Concentration Inequalities and Empirical Processes Theory Applied to the Analysis of Learning Algorithms

  • O. Bousquet
  • PhD thesis, Ecole Polytechnique,
  • 2002
Highly Influential
6 Excerpts

Asymptotics for transportation costs in high dimensions

  • V. Dobric, J. Yukich
  • J. Theor. Probab.,
  • 1995
Highly Influential
4 Excerpts

Weak Convergence and Empirical Processes

  • A. W. van der Vaart, J. A. Wellner
  • 1996
Highly Influential
1 Excerpt

Global geometry of SVM classifiers

  • D. Zhou, B. Xiao, H. Zhou, R. Dai
  • Technical Report 30-5-02,
  • 2002
2 Excerpts

Combinatorial Methods in Density Estimation

  • L. Devroye, G. Lugosi
  • 2001
1 Excerpt

Similar Papers

Loading similar papers…