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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bridges, D.: Foundations of Real and Abstract Analysis. In: Graduate Texts in Mathematics 174, Springer, New York (1998)
Hein, M., Bousquet, O.: Maximal Margin Classification for Metric Spaces. In: Proceedings of the 16th Conference on Learning Theory (COLT 2003), Washington DC (August 2003)
Juutinen, P.: Absolutely Minimizing Lipschitz Extensions on a Metric Space. Annales Academiæ Scientiarum Fennicæ Mathematica 27, 57–67 (2002)
McShane, E.J.: Extension of Range of Functions. Bulletin of the American Mathematical Society 40, 837–842 (1934)
von Luxburg, U., Bousquet, O.: Distance-Based Classification with Lipschitz Functions. In: Proceedings of the 16th Conference on Learning Theory (COLT 2003), Washington DC (August 2003)
Weaver, N.: Lipschitz Algebras. World Scientific, Singapore (1999)
Whitney, H.: Analytic Extensions of Differentiable Functions Defined in Closed Sets. Transactions of the American Mathematical Society 36(1), 63–89 (1934)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Minh, H.Q., Hofmann, T. (2004). Learning Over Compact Metric Spaces. In: Shawe-Taylor, J., Singer, Y. (eds) Learning Theory. COLT 2004. Lecture Notes in Computer Science(), vol 3120. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27819-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-27819-1_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22282-8
Online ISBN: 978-3-540-27819-1
eBook Packages: Springer Book Archive