Recurrent switching linear dynamical systems

Abstract

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.

15 pages, 6 figures

References in corpus (2)

• LFADS - Latent Factor Analysis via Dynamical Systems
• Dependent Multinomial Models Made Easy: Stick Breaking with the Pólya-Gamma Augmentation

Cited by in corpus (9)

• Dynamical Variational Autoencoders: A Comprehensive Review
• A New Spatial Count Data Model with Bayesian Additive Regression Trees for Accident Hot Spot Identification
• Learning Neural Event Functions for Ordinary Differential Equations
• Continuous Meta-Learning without Tasks
• Unsupervised learning of control signals and their encodings in $\text{C. elegans}$ whole-brain recordings
• Deep Explicit Duration Switching Models for Time Series
• Data Driven Estimation of Stochastic Switched Linear Systems of Unknown Order
• Inference of Dynamic Regimes in the Microbiome
• Scalable Hybrid HMM with Gaussian Process Emission for Sequential Time-series Data Clustering