Fast search for Dirichlet process mixture models

Details Fast search for Dirichlet process mixture models Fast search for Dirichlet process mixture models

2009-07-10

arxiv.org/abs/0907.1812v1

AIStats 2007

Computer Science

Learning

Scientific paper

Dirichlet process (DP) mixture models provide a flexible Bayesian framework for density estimation. Unfortunately, their flexibility comes at a cost: inference in DP mixture models is computationally expensive, even when conjugate distributions are used. In the common case when one seeks only a maximum a posteriori assignment of data points to clusters, we show that search algorithms provide a practical alternative to expensive MCMC and variational techniques. When a true posterior sample is desired, the solution found by search can serve as a good initializer for MCMC. Experimental results show that using these techniques is it possible to apply DP mixture models to very large data sets.

Affiliated with

Also associated with

No associations

Rating

Fast search for Dirichlet process mixture models does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Fast search for Dirichlet process mixture models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast search for Dirichlet process mixture models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-164734