Timezone: »

 
Poster
Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
Zhe Dong · Bryan Seybold · Kevin Murphy · Hung Bui

Thu Jul 16 08:00 AM -- 08:45 AM & Thu Jul 16 07:00 PM -- 07:45 PM (PDT) @
in Poster Session 43 »

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.

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

Author Information

Zhe Dong (Google)
Bryan Seybold (Google)
Kevin Murphy (Google Brain)
Hung Bui (VinAI Research)

More from the Same Authors