%0 Journal Article %1 wang_split-merge_2012 %A Wang, Chong %A Blei, David M. %D 2012 %J arXiv:1201.1657 %K Bayesian Carlo Learning, Machine Markov Monte algorithms, chain dirichlet, hierarchical inference, model, %T A Split-Merge MCMC Algorithm for the Hierarchical Dirichlet Process %U http://arxiv.org/abs/1201.1657 %X The hierarchical Dirichlet process (HDP) has become an important Bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where the number of components is determined by the data. As for most Bayesian nonparametric models, exact posterior inference is intractable---practitioners use Markov chain Monte Carlo (MCMC) or variational inference. Inspired by the split-merge MCMC algorithm for the Dirichlet process (DP) mixture model, we describe a novel split-merge MCMC sampling algorithm for posterior inference in the HDP. We study its properties on both synthetic data and text corpora. We find that split-merge MCMC for the HDP can provide significant improvements over traditional Gibbs sampling, and we give some understanding of the data properties that give rise to larger improvements.

@article{wang_split-merge_2012, abstract = {The hierarchical Dirichlet process (HDP) has become an important Bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where the number of components is determined by the data. As for most Bayesian nonparametric models, exact posterior inference is intractable---practitioners use Markov chain Monte Carlo (MCMC) or variational inference. Inspired by the split-merge MCMC algorithm for the Dirichlet process (DP) mixture model, we describe a novel split-merge MCMC sampling algorithm for posterior inference in the HDP. We study its properties on both synthetic data and text corpora. We find that split-merge MCMC for the HDP can provide significant improvements over traditional Gibbs sampling, and we give some understanding of the data properties that give rise to larger improvements.}, added-at = {2017-01-09T13:57:26.000+0100}, author = {Wang, Chong and Blei, David M.}, biburl = {https://www.bibsonomy.org/bibtex/2fe0e92bb0916fe706a102cd7469c532a/yourwelcome}, interhash = {3a6cf6c00e8c07faaac28867e64e53ec}, intrahash = {fe0e92bb0916fe706a102cd7469c532a}, journal = {arXiv:1201.1657}, keywords = {Bayesian Carlo Learning, Machine Markov Monte algorithms, chain dirichlet, hierarchical inference, model,}, month = jan, timestamp = {2017-01-09T14:01:11.000+0100}, title = {A {Split}-{Merge} {MCMC} {Algorithm} for the {Hierarchical} {Dirichlet} {Process}}, url = {http://arxiv.org/abs/1201.1657}, urldate = {2012-06-11}, year = 2012 }