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.

Appears in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998)

References in corpus (1)

• The Bayesian Structural EM Algorithm

Cited by in corpus (10)

• Empirical Analysis of Predictive Algorithms for Collaborative Filtering
• Causal Effect Inference with Deep Latent-Variable Models
• An Experimental Comparison of Several Clustering and Initialization Methods
• Gaussian Process Networks
• Loglinear models for first-order probabilistic reasoning
• On the Use of Skeletons when Learning in Bayesian Networks
• Sparse covariance estimation in heterogeneous samples
• Causal Structure Discovery from Distributions Arising from Mixtures of DAGs
• NOTMAD: Estimating Bayesian Networks with Sample-Specific Structures and Parameters
• Dis-entangling Mixture of Interventions on a Causal Bayesian Network Using Aggregate Observations