Recurrent switching linear dynamical systems
This work provides a method for gaining insight into natural systems like neural activity or sports movements, though it appears incremental as it builds on existing switching linear dynamical systems.
The authors tackled the problem of modeling complex nonlinear time series data by introducing recurrent switching linear dynamical systems, which discover dynamical units and explain their switching behavior based on observations or latent states, enabling scalable Bayesian inference.
Many natural systems, such as neurons firing in the brain or basketball teams traversing a court, give rise to time series data with complex, nonlinear dynamics. We can gain insight into these systems by decomposing the data into segments that are each explained by simpler dynamic units. Building on switching linear dynamical systems (SLDS), we present a new model class that not only discovers these dynamical units, but also explains how their switching behavior depends on observations or continuous latent states. These "recurrent" switching linear dynamical systems provide further insight by discovering the conditions under which each unit is deployed, something that traditional SLDS models fail to do. We leverage recent algorithmic advances in approximate inference to make Bayesian inference in these models easy, fast, and scalable.