Bayesian Nonparametric Inference of Switching Dynamic Linear Models

Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes. We consider two such models: the switching linear dynamical system (SLDS) and the switching vector autoregressive (VAR) process. Our Bayesian nonparametric approach utilizes a hierarchical Dirichlet process prior to learn an unknown number of persistent, smooth dynamical modes. We additionally employ automatic relevance determination to infer a sparse set of dynamic dependencies allowing us to learn SLDS with varying state dimension or switching VAR processes with varying autoregressive order. We develop a sampling algorithm that combines a truncated approximation to the Dirichlet process with efficient joint sampling of the mode and state sequences. The utility and flexibility of our model are demonstrated on synthetic data, sequences of dancing honey bees, the IBOVESPA stock index and a maneuvering target tracking application.

[1]  D. Blackwell,et al.  Ferguson Distributions Via Polya Urn Schemes , 1973 .

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

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

[4]  R. Moose,et al.  Modeling and Estimation for Tracking Maneuvering Targets , 1979, IEEE Transactions on Aerospace and Electronic Systems.

[5]  Lawrence R. Rabiner,et al.  A tutorial on Hidden Markov Models , 1986 .

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  James D. Hamilton A New Approach to the Economic Analysis of Nonstationary Time Series and the Business Cycle , 1989 .

[8]  J. Sethuraman A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[9]  M. Aoki,et al.  State space modeling of multiple time series , 1991 .

[10]  Chang‐Jin Kim,et al.  Dynamic linear models with Markov-switching , 1994 .

[11]  N. Shephard,et al.  Multivariate stochastic variance models , 1994 .

[12]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[13]  R. Kohn,et al.  Markov chain Monte Carlo in conditionally Gaussian state space models , 1996 .

[14]  Mike K. P. So,et al.  A Stochastic Volatility Model With Markov Switching , 1998 .

[15]  Brian D. O. Anderson,et al.  The Realization Problem for Hidden Markov Models , 1999, Math. Control. Signals Syst..

[16]  Geoffrey E. Hinton,et al.  Variational Learning for Switching State-Space Models , 2000, Neural Computation.

[17]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[18]  Vladimir Pavlovic,et al.  Learning Switching Linear Models of Human Motion , 2000, NIPS.

[19]  Carl E. Rasmussen,et al.  Factorial Hidden Markov Models , 1997 .

[20]  LI X.RONG,et al.  Survey of maneuvering target tracking. Part I. Dynamic models , 2003 .

[21]  R. Vidal,et al.  Observability and identifiability of jump linear systems , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[22]  Matthew J. Beal Variational algorithms for approximate Bayesian inference , 2003 .

[23]  X. R. Li,et al.  Survey of maneuvering target tracking. Part I. Dynamic models , 2003 .

[24]  S. Sastry,et al.  An algebraic geometric approach to the identification of a class of linear hybrid systems , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[25]  X. R. Li,et al.  Online Bayesian estimation of transition probabilities for Markovian jump systems , 2004, IEEE Transactions on Signal Processing.

[26]  Radford M. Neal,et al.  A Split-Merge Markov chain Monte Carlo Procedure for the Dirichlet Process Mixture Model , 2004 .

[27]  Yi Ma,et al.  Identification of hybrid linear time-invariant systems via subspace embedding and segmentation (SES) , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[28]  James M. Rehg,et al.  A data-driven approach to quantifying natural human motion , 2005, SIGGRAPH '05.

[29]  V. Jilkov,et al.  Survey of maneuvering target tracking. Part V. Multiple-model methods , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[30]  Zacharias Psaradakis,et al.  Joint Determination of the State Dimension and Autoregressive Order for Models with Markov Regime Switching , 2006 .

[31]  R. P. Marques,et al.  Discrete-Time Markov Jump Linear Systems , 2004, IEEE Transactions on Automatic Control.

[32]  A. Megretski,et al.  Model reduction of discrete-time Markov jump linear systems , 2006, 2006 American Control Conference.

[33]  Arnaud Doucet,et al.  Bayesian Inference for Dynamic Models with Dirichlet Process Mixtures , 2006, 2006 9th International Conference on Information Fusion.

[34]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[35]  René Vidal,et al.  Realization theory of stochastic jump-Markov linear systems , 2007, 2007 46th IEEE Conference on Decision and Control.

[36]  James M. Rehg,et al.  Learning and Inferring Motion Patterns using Parametric Segmental Switching Linear Dynamic Systems , 2008, International Journal of Computer Vision.

[37]  Carlos M. Carvalho,et al.  Simulation-based sequential analysis of Markov switching stochastic volatility models , 2007, Comput. Stat. Data Anal..

[38]  Søren Vang Andersen,et al.  Efficient Blind System Identification of Non-Gaussian Autoregressive Models With HMM Modeling of the Excitation , 2007, IEEE Transactions on Signal Processing.

[39]  Alan S. Willsky,et al.  Hierarchical Dirichlet processes for tracking maneuvering targets , 2007, 2007 10th International Conference on Information Fusion.

[40]  René Vidal,et al.  Identification of Hybrid Systems: A Tutorial , 2007, Eur. J. Control.

[41]  Kevin P. Murphy,et al.  Modeling changing dependency structure in multivariate time series , 2007, ICML '07.

[42]  Lawrence Carin,et al.  Music Analysis Using Hidden Markov Mixture Models , 2007, IEEE Transactions on Signal Processing.

[43]  Michael I. Jordan,et al.  An HDP-HMM for systems with state persistence , 2008, ICML '08.

[44]  Martin J. McKeown,et al.  A Hidden Markov, Multivariate Autoregressive (HMM-mAR) Network Framework for Analysis of Surface EMG (sEMG) Data , 2008, IEEE Transactions on Signal Processing.

[45]  Arnaud Doucet,et al.  Bayesian Inference for Linear Dynamic Models With Dirichlet Process Mixtures , 2007, IEEE Transactions on Signal Processing.

[46]  Michael I. Jordan,et al.  Nonparametric Bayesian Learning of Switching Linear Dynamical Systems , 2008, NIPS.

[47]  Michael I. Jordan,et al.  Nonparametric Bayesian Identification of Jump Systems with Sparse Dependencies , 2009 .

[48]  Emily B. Fox,et al.  Bayesian nonparametric learning of complex dynamical phenomena , 2009 .

[49]  Lawrence Carin,et al.  Hidden Markov Models With Stick-Breaking Priors , 2009, IEEE Transactions on Signal Processing.

[50]  A. Doucet,et al.  Particle Markov chain Monte Carlo methods , 2010 .

[51]  Michael I. Jordan,et al.  A Sticky HDP-HMM With Application to Speaker Diarization , 2009, 0905.2592.

[52]  W. Marsden I and J , 2012 .