Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems

10/21/2019
by   Zhe Dong, et al.
0

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) into meaningful "regimes", by using the piece-wise nonlinear dynamics.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 13

06/04/2021

Deep Switching State Space Model (DS^3M) for Nonlinear Time Series Forecasting with Regime Switching

We propose a deep switching state space model (DS^3M) for efficient infe...
05/11/2018

Robust and Scalable Models of Microbiome Dynamics

Microbes are everywhere, including in and on our bodies, and have been s...
07/14/2017

Variational approach for learning Markov processes from time series data

Inference, prediction and control of complex dynamical systems from time...
05/09/2021

Segmenting Hybrid Trajectories using Latent ODEs

Smooth dynamics interrupted by discontinuities are known as hybrid syste...
05/29/2018

Probabilistic Trajectory Segmentation by Means of Hierarchical Dirichlet Process Switching Linear Dynamical Systems

Using movement primitive libraries is an effective means to enable robot...
06/10/2021

Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features

Effectively modeling phenomena present in highly nonlinear dynamical sys...
06/18/2021

Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion

In this paper, we propose a Bayesian switching dynamical model for segme...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.