Propagating Kernel Ambiguity Sets in Nonlinear Data-driven Dynamics Models

by   Jia-Jie Zhu, et al.

This paper provides answers to an open problem: given a nonlinear data-driven dynamical system model, e.g., kernel conditional mean embedding (CME) and Koopman operator, how can one propagate the ambiguity sets forward for multiple steps? This problem is the key to solving distributionally robust control and learning-based control of such learned system models under a data-distribution shift. Different from previous works that use either static ambiguity sets, e.g., fixed Wasserstein balls, or dynamic ambiguity sets under known piece-wise linear (or affine) dynamics, we propose an algorithm that exactly propagates ambiguity sets through nonlinear data-driven models using the Koopman operator and CME, via the kernel maximum mean discrepancy geometry. Through both theoretical and numerical analysis, we show that our kernel ambiguity sets are the natural geometric structure for the learned data-driven dynamical system models.


page 1

page 2

page 3

page 4


PyKoopman: A Python Package for Data-Driven Approximation of the Koopman Operator

PyKoopman is a Python package for the data-driven approximation of the K...

Residuals-based distributionally robust optimization with covariate information

We consider data-driven approaches that integrate a machine learning pre...

Kernel Distributionally Robust Optimization

This paper is an in-depth investigation of using kernel methods to immun...

Data-Driven Chance Constrained Control using Kernel Distribution Embeddings

We present a data-driven algorithm for efficiently computing stochastic ...

Data-driven Koopman Operators for Model-based Shared Control of Human-Machine Systems

We present a data-driven shared control algorithm that can be used to im...

Data-Driven Encoding: A New Numerical Method for Computation of the Koopman Operator

This paper presents a data-driven method for constructing a Koopman line...

Please sign up or login with your details

Forgot password? Click here to reset