Learning over Compact Metric Spaces

Abstract

We consider the problem of learning on a compact metric space X in a functional analytic framework. For a dense subalgebra of Lip ( X ), the space of all Lipschitz functions on X , the Representer Theorem is derived. We obtain exact solutions in the case of least square minimization and regularization and suggest an approximate solution for the Lipschitz classifier.

Cite

Text

Minh and Hofmann. "Learning over Compact Metric Spaces." Annual Conference on Computational Learning Theory, 2004. doi:10.1007/978-3-540-27819-1_17

Markdown

[Minh and Hofmann. "Learning over Compact Metric Spaces." Annual Conference on Computational Learning Theory, 2004.](https://mlanthology.org/colt/2004/minh2004colt-learning/) doi:10.1007/978-3-540-27819-1_17

BibTeX

@inproceedings{minh2004colt-learning,
  title     = {{Learning over Compact Metric Spaces}},
  author    = {Minh, Ha Quang and Hofmann, Thomas},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2004},
  pages     = {239-254},
  doi       = {10.1007/978-3-540-27819-1_17},
  url       = {https://mlanthology.org/colt/2004/minh2004colt-learning/}
}