Single Trajectory Nonparametric Learning of Nonlinear Dynamics

by   Ingvar Ziemann, et al.

Given a single trajectory of a dynamical system, we analyze the performance of the nonparametric least squares estimator (LSE). More precisely, we give nonasymptotic expected l^2-distance bounds between the LSE and the true regression function, where expectation is evaluated on a fresh, counterfactual, trajectory. We leverage recently developed information-theoretic methods to establish the optimality of the LSE for nonparametric hypotheses classes in terms of supremum norm metric entropy and a subgaussian parameter. Next, we relate this subgaussian parameter to the stability of the underlying process using notions from dynamical systems theory. When combined, these developments lead to rate-optimal error bounds that scale as T^-1/(2+q) for suitably stable processes and hypothesis classes with metric entropy growth of order δ^-q. Here, T is the length of the observed trajectory, δ∈ℝ_+ is the packing granularity and q∈ (0,2) is a complexity term. Finally, we specialize our results to a number of scenarios of practical interest, such as Lipschitz dynamics, generalized linear models, and dynamics described by functions in certain classes of Reproducing Kernel Hilbert Spaces (RKHS).


page 1

page 2

page 3

page 4


Ensemble forecasts in reproducing kernel Hilbert space family: dynamical systems in Wonderland

A methodological framework for ensemble-based estimation and simulation ...

Bless and curse of smoothness and phase transitions in nonparametric regressions: a nonasymptotic perspective

When the regression function belongs to the standard smooth classes cons...

Metric on Nonlinear Dynamical Systems with Koopman Operators

The development of a metric for structural data is a long-term problem i...

Efficient Learning of a Linear Dynamical System with Stability Guarantees

We propose a principled method for projecting an arbitrary square matrix...

Modeling of Missing Dynamical Systems: Deriving Parametric Models using a Nonparametric Framework

In this paper, we consider modeling missing dynamics with a non-Markovia...

Learning Stability Certificates from Data

Many existing tools in nonlinear control theory for establishing stabili...

Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularization

We propose a novel framework for learning stabilizable nonlinear dynamic...