PO-MOESP subspace identification of Directed Acyclic Graphs with unknown topology

In this paper, a PO-MOESP subspace identification algorithm for Directed Acyclic Graphs (DAG) is presented. The state of every node and the structure of the graph are assumed to be unknown. The method estimates the column space of the observability matrix of every node by projecting away the input-output data from the rest of the graph. A past input-output instrumental variable (IV) approach is adopted to deal with the noise. The topology of the network is revealed by using dedicated projection matrices. Moreover, we provide a characterization of the class of graphs whose topology can be fully reconstructed by using this method. Finally, two simulation examples are provided to show the effectiveness of the proposed methodology.

[1]  Lorenz Huelsbergen,et al.  Dynamic resolution: A runtime technique for the parallelization of modifications to directed acyclic graphs , 1997, International Journal of Parallel Programming.

[2]  Alessandro Chiuso,et al.  Learning sparse dynamic linear systems using stable spline kernels and exponential hyperpriors , 2010, NIPS.

[3]  Catherine Roucairol,et al.  Graph Partitioning Applied to the Logic Testing of Combinational Circuits , 1995, Discret. Appl. Math..

[4]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[5]  Tandy J. Warnow,et al.  Phylogenetic networks: modeling, reconstructibility, and accuracy , 2004, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[6]  Judea Pearl,et al.  Causal networks: semantics and expressiveness , 2013, UAI.

[7]  D. Materassi.  Reconstruction of topologies for acyclic networks of dynamical systems , 2011, Proceedings of the 2011 American Control Conference.

[8]  Bhaskar D. Rao,et al.  Sparse Bayesian learning for basis selection , 2004, IEEE Transactions on Signal Processing.

[9]  H. Akaike.  A new look at the statistical model identification , 1974 .

[10]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[11]  P. Spirtes,et al.  An Algorithm for Fast Recovery of Sparse Causal Graphs , 1991 .

[12]  Patrick Dewilde,et al.  Subspace model identification Part 1. The output-error state-space model identification class of algorithms , 1992 .

[13]  D. Botstein,et al.  Cluster analysis and display of genome-wide expression patterns. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Shahin Shahrampour,et al.  Reconstruction of directed networks from consensus dynamics , 2013, 2013 American Control Conference.

[15]  Gregory Gutin,et al.  Digraphs - theory, algorithms and applications , 2002 .

[16]  Alessandro Chiuso,et al.  The role of vector autoregressive modeling in predictor-based subspace identification , 2007, Autom..

[17]  Ravi Mazumdar,et al.  Inferring causality in networks of WSS processes by pairwise estimation methods , 2013, 2013 Information Theory and Applications Workshop (ITA).

[18]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series , 1964 .

[19]  Iven M. Y. Mareels,et al.  Control of Large-Scale Irrigation Networks , 2007, Proceedings of the IEEE.

[20]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[21]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[22]  大西 仁,et al.  Pearl, J. (1988, second printing 1991). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan-Kaufmann. , 1994 .

[23]  Gene H. Golub,et al.  Matrix computations , 1983 .

[24]  Stephen J. Roberts,et al.  Probabilistic Modeling in Bioinformatics and Medical Informatics , 2010 .

[25]  Adel Javanmard,et al.  Learning Linear Bayesian Networks with Latent Variables , 2012, ICML.

[26]  Zoubin Ghahramani,et al.  Modeling genetic regulatory networks using gene expression profiling and state space models , 2005 .

[27]  Martin A. Nowak,et al.  Inferring Cellular Networks Using Probabilistic Graphical Models , 2004 .

[28]  Jan-Willem van Wingerden,et al.  A model-free distributed approach for wind plant control , 2013, 2013 American Control Conference.

[29]  V. Verdult,et al.  Filtering and System Identification: A Least Squares Approach , 2007 .

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

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

[32]  Donatello Materassi,et al.  Topological identification in networks of dynamical systems , 2008, 2008 47th IEEE Conference on Decision and Control.

[33]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[34]  Todd P. Coleman,et al.  Estimating the directed information to infer causal relationships in ensemble neural spike train recordings , 2010, Journal of Computational Neuroscience.

[35]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[36]  Mark Smotherman,et al.  Efficient DAG construction and heuristic calculation for instruction scheduling , 1991, MICRO 24.

[37]  Donatello Materassi,et al.  Modeling the topology of a dynamical network via Wiener filtering approach , 2012, Autom..

[38]  R. Horowitz,et al.  Control design of an automated highway system , 2000, Proceedings of the IEEE.

[39]  Alessandro Chiuso,et al.  A Bayesian approach to sparse dynamic network identification , 2012, Autom..

[40]  Alessandro Chiuso,et al.  On the relation between CCA and predictor-based subspace identification. , 2005, CDC 2005.

[41]  Magnus Egerstedt,et al.  Network discovery: An estimation based approach , 2011, Proceedings of the 2011 American Control Conference.

[42]  Pablo A. Parrilo,et al.  Rank-Sparsity Incoherence for Matrix Decomposition , 2009, SIAM J. Optim..

[43]  Bart De Moor,et al.  N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems , 1994, Autom..

[44]  Xu Peiliang,et al.  Overview of Total Least Squares Methods , 2013 .