Construction of Dependent Dirichlet Processes based on Poisson Processes

We present a novel method for constructing dependent Dirichlet processes. The approach exploits the intrinsic relationship between Dirichlet and Poisson processes in order to create a Markov chain of Dirichlet processes suitable for use as a prior over evolving mixture models. The method allows for the creation, removal, and location variation of component models over time while maintaining the property that the random measures are marginally DP distributed. Additionally, we derive a Gibbs sampling algorithm for model inference and test it on both synthetic and real data. Empirical results demonstrate that the approach is effective in estimating dynamically varying mixture models.

[1]  J. Sethuraman.  A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[2]  Carl E. Rasmussen,et al.  The Infinite Gaussian Mixture Model , 1999, NIPS.

[3]  M. Escobar,et al.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[4]  S. MacEachern.  Decision Theoretic Aspects of Dependent Nonparametric Processes , 2000 .

[5]  Michael I. Jordan,et al.  Learning Spectral Clustering , 2003, NIPS.

[6]  P. Müller,et al.  A method for combining inference across related nonparametric Bayesian models , 2004 .

[7]  Marina Meila,et al.  Comparing clusterings: an axiomatic view , 2005, ICML.

[8]  J. Lafferty,et al.  Time-Sensitive Dirichlet Process Mixture Models , 2005 .

[9]  S. Roweis,et al.  Time-Varying Topic Models using Dependent Dirichlet Processes , 2005 .

[10]  J. E. Griffin,et al.  Order-Based Dependent Dirichlet Processes , 2006 .

[11]  Eric P. Xing,et al.  Hidden Markov Dirichlet Process: Modeling Genetic Recombination in Open Ancestral Space , 2006, NIPS.

[12]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[13]  D. Dunson.  Bayesian dynamic modeling of latent trait distributions. , 2006, Biostatistics.

[14]  Arnaud Doucet,et al.  Generalized Polya Urn for Time-varying Dirichlet Process Mixtures , 2007, UAI.

[15]  Michael I. Jordan,et al.  Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[16]  David M. Blei,et al.  Syntactic Topic Models , 2008, NIPS.

[17]  Eric P. Xing,et al.  Dynamic Non-Parametric Mixture Models and the Recurrent Chinese Restaurant Process: with Applications to Evolutionary Clustering , 2008, SDM.

[18]  David B. Dunson,et al.  The dynamic hierarchical Dirichlet process , 2008, ICML '08.

[19]  M. Steel,et al.  Time-dependent stick-breaking processes , 2009 .

[20]  Yee Whye Teh,et al.  Spatial Normalized Gamma Processes , 2009, NIPS.

[21]  W. Eric L. Grimson,et al.  Learning visual flows: A Lie algebraic approach , 2009, CVPR.

[22]  M. R. Leadbetter.  Poisson Processes , 2011, International Encyclopedia of Statistical Science.

[23]  D. Dunson,et al.  The local Dirichlet process , 2011, Annals of the Institute of Statistical Mathematics.