On the annealed VC entropy for margin classifiers: A statistical mechanics study

Opper, Manfred (1998). On the annealed VC entropy for margin classifiers: A statistical mechanics study. IN: Advances in Kernel Methods - Support vector learning. Scholkopf, Bernhard; Burges, Christopher J. C. and Smola, Alexander J. (eds) Cambridge, MA: MIT.

Abstract

Using techniques from Statistical Physics, the annealed VC entropy for hyperplanes in high dimensional spaces is calculated as a function of the margin for a spherical Gaussian distribution of inputs.

Divisions: Aston University (General)
Additional Information: Copyright of the Massachusetts Institute of Technology Press (MIT Press) Available in Google Books
Uncontrolled Keywords: annealed VC entropy,hyperplanes,high dimensional spaces,spherical Gaussian distribution
Full Text Link:
Related URLs: http://mitpress ... type=2&tid=7841 (Publisher URL)
Published Date: 1998-12-18
Authors: Opper, Manfred

Download

[img]

Version: Accepted Version


Export / Share Citation


Statistics

Additional statistics for this record