Generalized Polya Urn for Time-Varying Dirichlet Process Mixtures

Francois Caron, Manuel Davy, Arnaud Doucet

UAI 2007 pp. 33-40

doi:10.5555/3020488.3020493 /uai/2007/caron2007uai-generalized/

Abstract

Dirichlet Process Mixtures (DPMs) are a popular class of statistical models to perform density estimation and clustering. However, when the data available have a distribution evolving over time, such models are inadequate. We introduce here a class of time-varying DPMs which ensures that at each time step the random distribution follows a DPM model. Our model relies on an intuitive and simple generalized Polya urn scheme. Inference is performed using Markov chain Monte Carlo and Sequential Monte Carlo. We demonstrate our model on various applications.

UAI Semantic Scholar

Cite

Text

Caron et al. "Generalized Polya Urn for Time-Varying Dirichlet Process Mixtures." Conference on Uncertainty in Artificial Intelligence, 2007. doi:10.5555/3020488.3020493

Markdown

[Caron et al. "Generalized Polya Urn for Time-Varying Dirichlet Process Mixtures." Conference on Uncertainty in Artificial Intelligence, 2007.](https://mlanthology.org/uai/2007/caron2007uai-generalized/) doi:10.5555/3020488.3020493

BibTeX

@inproceedings{caron2007uai-generalized,
  title     = {{Generalized Polya Urn for Time-Varying Dirichlet Process Mixtures}},
  author    = {Caron, Francois and Davy, Manuel and Doucet, Arnaud},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2007},
  pages     = {33-40},
  doi       = {10.5555/3020488.3020493},
  url       = {https://mlanthology.org/uai/2007/caron2007uai-generalized/}
}