Exponential families and simplification of mixture models

Presentation of the exponential families, of the mixtures of such distributions and how to learn it. We then present algorithms to simplify mixture model, using Kullback-Leibler divergence and Fisher metric. See the attached extended abstract for more info.

• Authors: Olivier Schwander, Frank Nielsen
• Attachments: 1 file(s)
• Keywords: Bregman Divergence, Clustering, Exponential Family, Kernel Density Estimation, Mixture Models