Computer Science Department
School of Computer Science, Carnegie Mellon University


Bounds for Averaging Classifiers

John Langford+, Matthias Seeger*

January 2001

Keywords: PAC bound, Maximum entropy discrimination, averaging hypotheses

We present a generalized PAC bound for averaging classifiers which applies to base hypotheses with a bounded real valued output. In addition, we discuss several methods for quantitatively tightening the bound. In the process, a tightened version of the PAC-Bayes bound is proved.

15 pages,
*Institute for Adaptive and Neural Computation, University of Edinburgh,,

Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by