Deep Variational Koopman Models: Inferring Koopman Observations for Uncertainty-Aware Dynamics Modeling and Control

by   Jeremy Morton, et al.
Stanford University

Koopman theory asserts that a nonlinear dynamical system can be mapped to a linear system, where the Koopman operator advances observations of the state forward in time. However, the observable functions that map states to observations are generally unknown. We introduce the Deep Variational Koopman (DVK) model, a method for inferring distributions over observations that can be propagated linearly in time. By sampling from the inferred distributions, we obtain a distribution over dynamical models, which in turn provides a distribution over possible outcomes as a modeled system advances in time. Experiments show that the DVK model is effective at long-term prediction for a variety of dynamical systems. Furthermore, we describe how to incorporate the learned models into a control framework, and demonstrate that accounting for the uncertainty present in the distribution over dynamical models enables more effective control.


page 1

page 2

page 3

page 4


Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems

Filtering is a general name for inferring the states of a dynamical syst...

A Deep Learning Approach for Characterizing Major Galaxy Mergers

Fine-grained estimation of galaxy merger stages from observations is a k...

Attractor Stability in Finite Asynchronous Biological System Models

We present mathematical techniques for exhaustive studies of long-term d...

Predictive State Representations: A New Theory for Modeling Dynamical Systems

Modeling dynamical systems, both for control purposes and to make predic...

A Local Information Criterion for Dynamical Systems

Encoding a sequence of observations is an essential task with many appli...

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems

Given an unknown dynamical system, what is the minimum number of samples...

Distribution Preserving Multiple Hypotheses Prediction for Uncertainty Modeling

Many supervised machine learning tasks, such as future state prediction ...

Please sign up or login with your details

Forgot password? Click here to reset