Efficient Classification for Metric Data

  title={Efficient Classification for Metric Data},
  author={Lee-Ad Gottlieb and Aryeh Kontorovich and Robert Krauthgamer},
  journal={IEEE Transactions on Information Theory},
Recent advances in large-margin classification of data residing in general metric spaces (rather than Hilbert spaces) enable classification under various natural metrics, such as string edit and earthmover distance. A general framework developed for this purpose left open the questions of computational efficiency and of providing direct bounds on generalization error. We design a new algorithm for classification in general metric spaces, whose runtime and accuracy depend on the doubling… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 5 times over the past 90 days. VIEW TWEETS
0 Extracted Citations
50 Extracted References
Similar Papers