Learning Mixtures of DAG Models
Abstract
We describe computationally efficient methods for learning mixtures in which each component is a directed acyclic graphical model (mixtures of DAGs or MDAGs). We argue that simple search-and-score algorithms are infeasible for a variety of problems, and introduce a feasible approach in which parameter and structure search is interleaved and expected data is treated as real data. Our approach can be viewed as a combination of (1) the Cheeseman-Stutz asymptotic approximation for model posterior probability and (2) the Expectation-Maximization algorithm. We evaluate our procedure for selecting among MDAGs on synthetic and real examples.
Cite
Text
Thiesson et al. "Learning Mixtures of DAG Models." Conference on Uncertainty in Artificial Intelligence, 1998.Markdown
[Thiesson et al. "Learning Mixtures of DAG Models." Conference on Uncertainty in Artificial Intelligence, 1998.](https://mlanthology.org/uai/1998/thiesson1998uai-learning/)BibTeX
@inproceedings{thiesson1998uai-learning,
title = {{Learning Mixtures of DAG Models}},
author = {Thiesson, Bo and Meek, Christopher and Chickering, David Maxwell and Heckerman, David},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {1998},
pages = {504-513},
url = {https://mlanthology.org/uai/1998/thiesson1998uai-learning/}
}