|| The Switching Hierarchical Gaussian Filter
||Ismail Senoz, Semih Akbayrak, Albert Podusenko, PhD candidate/ Technical University of Eindhoven, Netherlands; Christoph Mathys, Aarhus University, Denmark; Bert de Vries, Eindhoven University of Technology, Netherlands|
||D3-S6-T3: Message Passing
||Wednesday, 14 July, 23:40 - 00:00
||Thursday, 15 July, 00:00 - 00:20
In this paper we discuss variational message passing-based (VMP) inference in a switching Hierarchical GaussianFilter (HGF). An HGF is a flexible hierarchical state space model that supports closed-form VMP-based approximate inference for tracking of both states and slowly time-varying parameters.Since natural signals often submit to regime-switching dynamics, there is a need for low-complexity closed-form inference in switching state space models. Here we extend the HGF model with parameter switching mechanics and derive closed-formVMP update rules for plug-in applications in factor graph-based models. These VMP rules support both tracking of latent variables and variational free energy as a model performance measure. We show that the switching HGF performs better than a non-switching HGF on modelling of a stock market data set.