ML Anthology

Learning with Tree-Averaged Densities and Distributions

Sergey Kirshner
NeurIPS 2007 pp. 761-768
/neurips/2007/kirshner2007neurips-learning/

Abstract

We utilize the ensemble of trees framework, a tractable mixture over super- exponential number of tree-structured distributions [1], to develop a new model for multivariate density estimation. The model is based on a construction of tree- structured copulas – multivariate distributions with uniform on [0, 1] marginals. By averaging over all possible tree structures, the new model can approximate distributions with complex variable dependencies. We propose an EM algorithm to estimate the parameters for these tree-averaged models for both the real-valued and the categorical case. Based on the tree-averaged framework, we propose a new model for joint precipitation amounts data on networks of rain stations.

PDF NeurIPS Semantic Scholar

Cite

Text

Kirshner. "Learning with Tree-Averaged Densities and Distributions." Neural Information Processing Systems, 2007.

Markdown

[Kirshner. "Learning with Tree-Averaged Densities and Distributions." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/kirshner2007neurips-learning/)

BibTeX

@inproceedings{kirshner2007neurips-learning,
  title     = {{Learning with Tree-Averaged Densities and Distributions}},
  author    = {Kirshner, Sergey},
  booktitle = {Neural Information Processing Systems},
  year      = {2007},
  pages     = {761-768},
  url       = {https://mlanthology.org/neurips/2007/kirshner2007neurips-learning/}
}