ML Anthology

Tempering for Bayesian C&RT

Nicos Angelopoulos, James Cussens
ICML 2005 pp. 17-24
doi:10.1145/1102351.1102354 /icml/2005/angelopoulos2005icml-tempering/

Abstract

This paper concerns the experimental assessment of tempering as a technique for improving Bayesian inference for C&RT models. Full Bayesian inference requires the computation of a posterior over all possible trees. Since exact computation is not possible Markov chain Monte Carlo (MCMC) methods are used to produce an approximation. C&RT posteriors have many local modes: tempering aims to prevent the Markov chain getting stuck in these modes. Our results show that a clear improvement is achieved using tempering.

PDF ICML Semantic Scholar

Cite

Text

Angelopoulos and Cussens. "Tempering for Bayesian C&RT." International Conference on Machine Learning, 2005. doi:10.1145/1102351.1102354

Markdown

[Angelopoulos and Cussens. "Tempering for Bayesian C&RT." International Conference on Machine Learning, 2005.](https://mlanthology.org/icml/2005/angelopoulos2005icml-tempering/) doi:10.1145/1102351.1102354

BibTeX

@inproceedings{angelopoulos2005icml-tempering,
  title     = {{Tempering for Bayesian C&RT}},
  author    = {Angelopoulos, Nicos and Cussens, James},
  booktitle = {International Conference on Machine Learning},
  year      = {2005},
  pages     = {17-24},
  doi       = {10.1145/1102351.1102354},
  url       = {https://mlanthology.org/icml/2005/angelopoulos2005icml-tempering/}
}