Bayesian Hierarchical Clustering Export

@inproceedings{heller2005bayesian, abstract = {We present a novel algorithm for agglomerative hierarchical clustering based on evaluating marginal likelihoods of a probabilistic model. This algorithm has several advantages over traditional distance-based agglomerative clustering algorithms. (1) It defines a probabilistic model of the data which can be used to compute the predictive distribution of a test point and the probability of it belonging to any of the existing clusters in the tree. (2) It uses a model-based criterion to decide on merging clusters rather than an ad-hoc distance metric. (3) Bayesian hypothesis testing is used to decide which merges are advantageous and to output the recommended depth of the tree. (4) The algorithm can be interpreted as a novel fast bottom-up approximate inference method for a Dirichlet process (i.e. countably infinite) mixture model (DPM). It provides a new lower bound on the marginal likelihood of a DPM by summing over exponentially many clusterings of the data in polynomial time. We describe procedures for learning the model hyperparameters, computing the predictive distribution, and extensions to the algorithm. Experimental results on synthetic and real-world data sets demonstrate useful properties of the algorithm.}, author = {Heller, Katherine A. and Ghahramani, Zoubin}, booktitle = {In Twenty-second International Conference on Machine Learning}, citeulike-article-id = {5175621}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.7791}, keywords = {bayesian, clustering}, pages = {297--304}, posted-at = {2009-07-16 08:27:53}, priority = {2}, title = {Bayesian Hierarchical Clustering}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.7791}, volume = {22}, year = {2005} }

TY - CONF ID - heller2005bayesian L3 - citeulike-article-id:5175621 N2 - We present a novel algorithm for agglomerative hierarchical clustering based on evaluating marginal likelihoods of a probabilistic model. This algorithm has several advantages over traditional distance-based agglomerative clustering algorithms. (1) It defines a probabilistic model of the data which can be used to compute the predictive distribution of a test point and the probability of it belonging to any of the existing clusters in the tree. (2) It uses a model-based criterion to decide on merging clusters rather than an ad-hoc distance metric. (3) Bayesian hypothesis testing is used to decide which merges are advantageous and to output the recommended depth of the tree. (4) The algorithm can be interpreted as a novel fast bottom-up approximate inference method for a Dirichlet process (i.e. countably infinite) mixture model (DPM). It provides a new lower bound on the marginal likelihood of a DPM by summing over exponentially many clusterings of the data in polynomial time. We describe procedures for learning the model hyperparameters, computing the predictive distribution, and extensions to the algorithm. Experimental results on synthetic and real-world data sets demonstrate useful properties of the algorithm. EP - 304 TI - Bayesian Hierarchical Clustering VL - 22 T2 - In Twenty-second International Conference on Machine Learning SP - 297 KW - bayesian KW - clustering AU - Heller, Katherine AU - Ghahramani, Zoubin PY - 2005/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.7791 ER -