Learning Mixtures of Tree Graphical Models

Abstract

We consider unsupervised estimation of mixtures of discrete graphical models, where the class variable is hidden and each mixture component can have a potentially different Markov graph structure and parameters over the observed variables. We propose a novel method for estimating the mixture components with provable guarantees. Our output is a tree-mixture model which serves as a good approximation to the underlying graphical model mixture. The sample and computational requirements for our method scale as $\poly(p, r)$, for an $r$-component mixture of $p$-variate graphical models, for a wide class of models which includes tree mixtures and mixtures over bounded degree graphs.

Cite

Text

Anandkumar et al. "Learning Mixtures of Tree Graphical Models." Neural Information Processing Systems, 2012.

Markdown

[Anandkumar et al. "Learning Mixtures of Tree Graphical Models." Neural Information Processing Systems, 2012.](https://mlanthology.org/neurips/2012/anandkumar2012neurips-learning/)

BibTeX

@inproceedings{anandkumar2012neurips-learning,
  title     = {{Learning Mixtures of Tree Graphical Models}},
  author    = {Anandkumar, Anima and Hsu, Daniel J. and Huang, Furong and Kakade, Sham M.},
  booktitle = {Neural Information Processing Systems},
  year      = {2012},
  pages     = {1052-1060},
  url       = {https://mlanthology.org/neurips/2012/anandkumar2012neurips-learning/}
}