Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lübsen, Jannis, Eichler, Annika
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.05798
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917388296912896
author Lübsen, Jannis
Eichler, Annika
author_facet Lübsen, Jannis
Eichler, Annika
contents This paper proposes a method for constructing one-step prediction tubes for nonlinear systems using reproducing kernel Hilbert spaces. We approximate a bounded reproducing kernel Hilbert space (RKHS) hypothesis set by a finite-dimensional subspace using bounds based on n-widths and a greedy algorithm for basis reduction. For kernels whose native spaces are norm-equivalent to Sobolev spaces, we derive how the required basis size scales with kernel smoothness and input dimension. This finite-dimensional representation enables the use of convex scenario optimization to obtain violation guarantees for the learned predictor without requiring an a priori bound on the true system's RKHS norm or Lipschitz constant. The method is demonstrated on an obstacle-avoidance task. We also discuss the main limitations of the current analysis, including dimensional scaling and dependence on i.i.d. data.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05798
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Nonlinear System Identification in Reproducing Kernel Hilbert Spaces via Scenario Optimization
Lübsen, Jannis
Eichler, Annika
Systems and Control
This paper proposes a method for constructing one-step prediction tubes for nonlinear systems using reproducing kernel Hilbert spaces. We approximate a bounded reproducing kernel Hilbert space (RKHS) hypothesis set by a finite-dimensional subspace using bounds based on n-widths and a greedy algorithm for basis reduction. For kernels whose native spaces are norm-equivalent to Sobolev spaces, we derive how the required basis size scales with kernel smoothness and input dimension. This finite-dimensional representation enables the use of convex scenario optimization to obtain violation guarantees for the learned predictor without requiring an a priori bound on the true system's RKHS norm or Lipschitz constant. The method is demonstrated on an obstacle-avoidance task. We also discuss the main limitations of the current analysis, including dimensional scaling and dependence on i.i.d. data.
title Robust Nonlinear System Identification in Reproducing Kernel Hilbert Spaces via Scenario Optimization
topic Systems and Control
url https://arxiv.org/abs/2604.05798