Fox, Emily BSudderth, Erik BJordan, Michael IWillsky, Alan S2023-05-232023-05-232009-01-012016-08-11https://repository.upenn.edu/handle/20.500.14332/47588Many nonlinear 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 nonparametric Bayesian approach utilizes a hierarchical Dirichlet process prior to learn an unknown number of persistent, smooth dynamical modes. 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, and the IBOVESPA stock index.© 2009. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.jump processesnon-parametric identificationstochastic realizationmachine learningdynamic systemsMarkov modelsstate-space modelsautoregressive processesStatistics and ProbabilityArticle