Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems

Zhe Dong · Bryan Seybold · Kevin Murphy · Hung Bui

Keywords: [ Approximate Inference ] [ Deep Sequence Models ] [ Generative Models ] [ Time Series and Sequence Models ] [ Sequential, Network, and Time-Series Modeling ]


We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.

Chat is not available.