Learning Intersections of Halfspaces with a Margin.
A. Klivans and R. Servedio.
Journal of Computer and System Sciences 74: 35-49, 2008.
Preliminary version in Seventeenth Annual Conference on Computational Learning Theory (COLT), 2004, pp. 348-362.


We give a new algorithm for learning intersections of halfspaces with a margin, i.e. under the assumption that no example lies too close to any separating hyperplane. Our algorithm combines random projection techniques for dimensionality reduction, polynomial threshold function constructions, and kernel methods. The algorithm is fast and simple. It learns a broader class of functions and achieves an exponential runtime improvement compared with previous work on learning intersections of halfspaces with a margin.

Postscript or pdf (full version of conference paper)

pdf of journal version

Back to main papers page