University of Cambridge > > Machine Learning @ CUED > H-Infinity Clustering

H-Infinity Clustering

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

Normally in clustering we try to optimize some average distortion between the items and the prototypes. I’ll review a setup for clustering (vector quantization) in which the quantity of interest is the worst distortion between any item and its chosen prototype. Optimizing this (or a bound on it) creates a minimax problem similar to problems with a rich history in control theory and operations research. I’ll review a linear programming relaxation which solves the problem and discuss extensions to the setting of classification.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity