ML Anthology

Beam Sampling for the Infinite Hidden Markov Model

Jurgen Van Gael, Yunus Saatci, Yee Whye Teh, Zoubin Ghahramani
ICML 2008 pp. 1088-1095
doi:10.1145/1390156.1390293 /icml/2008/gael2008icml-beam/

Abstract

The infinite hidden Markov model is a nonparametric extension of the widely used hidden Markov model. Our paper introduces a new inference algorithm for the infinite hidden Markov model called beam sampling. Beam sampling combines slice sampling, which limits the number of states considered at each time step to a finite number, with dynamic programming, which samples whole state trajectories efficiently. Our algorithm typically outperforms the Gibbs sampler and is more robust. We present applications of iHMM inference using the beam sampler on changepoint detection and text prediction problems.

PDF ICML Semantic Scholar

Cite

Text

Van Gael et al. "Beam Sampling for the Infinite Hidden Markov Model." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390293

Markdown

[Van Gael et al. "Beam Sampling for the Infinite Hidden Markov Model." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/gael2008icml-beam/) doi:10.1145/1390156.1390293

BibTeX

@inproceedings{gael2008icml-beam,
  title     = {{Beam Sampling for the Infinite Hidden Markov Model}},
  author    = {Van Gael, Jurgen and Saatci, Yunus and Teh, Yee Whye and Ghahramani, Zoubin},
  booktitle = {International Conference on Machine Learning},
  year      = {2008},
  pages     = {1088-1095},
  doi       = {10.1145/1390156.1390293},
  url       = {https://mlanthology.org/icml/2008/gael2008icml-beam/}
}