FastEx: Hash Clustering with Exponential Families
Amr AbdelFatah Ahmed, Sujith Ravi, Alex J. Smola, Shravan Narayanamurthy · 2012
Clustering is a key component in any data analysis toolbox. Despite its impor-tance, scalable algorithms often eschew rich statistical models in favor of simpler descriptions such as k-means clustering. In this paper we present a sampler, ca-pable of estimating mixtures of exponential families. At its heart lies a novel proposal distribution using random projections to achieve high throughput in gen-erating proposals, which is crucial for clustering models with large numbers of clusters. 1