Counting and Uniform Sampling from Markov Equivalent DAGs

We propose an exact solution for the problem of finding the size of a Markov equivalence class (MEC). For the bounded degree graphs, the proposed solution is capable of computing the size of the MEC in polynomial time. Our proposed approach is based on a recursive method for counting the number of the elements of the MEC when a specific vertex is set as the source variable. We will further use the idea to design a sampler, which is capable of sampling from an MEC uniformly in polynomial time.

[1]  K. Sachs,et al.  Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data , 2005, Science.

[2]  Elias Bareinboim,et al.  Budgeted Experiment Design for Causal Structure Learning , 2017, ICML.

[3]  Aapo Hyvärinen,et al.  Causal discovery of linear acyclic models with arbitrary distributions , 2008, UAI.

[4]  Bin Yu,et al.  Formulas for Counting the Sizes of Markov Equivalence Classes of Directed Acyclic Graphs , 2016, ArXiv.

[5]  Christopher Meek,et al.  Causal inference and causal explanation with background knowledge , 1995, UAI.

[6]  Bin Yu,et al.  Reversible MCMC on Markov equivalence classes of sparse directed acyclic graphs , 2012, ArXiv.

[7]  M. Maathuis,et al.  Estimating the effect of joint interventions from observational data in sparse high-dimensional settings , 2014, 1407.2451.

[8]  Judea Pearl,et al.  Equivalence and Synthesis of Causal Models , 1990, UAI.

[9]  Preetam Nandy,et al.  Structure Learning of Linear Gaussian Structural Equation Models with Weak Edges , 2017, UAI.

[10]  Bin Yu,et al.  Counting and exploring sizes of Markov equivalence classes of directed acyclic graphs , 2015, J. Mach. Learn. Res..

[11]  Peter Bühlmann,et al.  Characterization and Greedy Learning of Interventional Markov Equivalence Classes of Directed Acyclic Graphs (Abstract) , 2011, UAI.

[12]  Yangbo He,et al.  Active Learning of Causal Networks with Intervention Experiments and Optimal Designs , 2008 .

[13]  R Scheines,et al.  The TETRAD Project: Constraint Based Aids to Causal Model Specification. , 1998, Multivariate behavioral research.

[14]  Frederick Eberhardt,et al.  On the Number of Experiments Sufficient and in the Worst Case Necessary to Identify All Causal Relations Among N Variables , 2005, UAI.

[15]  P. Spirtes,et al.  Causation, prediction, and search , 1993 .

[16]  Prasad Tetali,et al.  On sampling graphical Markov models , 2017 .

[17]  Michael D. Perlman,et al.  The size distribution for Markov equivalence classes of acyclic digraph models , 2002, Artif. Intell..

[18]  Bernhard Schölkopf,et al.  Elements of Causal Inference: Foundations and Learning Algorithms , 2017 .

[19]  Marloes H. Maathuis,et al.  Interpreting and Using CPDAGs With Background Knowledge , 2017, UAI.

[20]  Yuhao Wang,et al.  Permutation-based Causal Inference Algorithms with Interventions , 2017, NIPS.

[21]  D. Madigan,et al.  A characterization of Markov equivalence classes for acyclic digraphs , 1997 .