Saved in:
Bibliographic Details
Main Authors: Caldarelli, Edoardo, Chatalic, Antoine, Colomé, Adrià, Molinari, Cesare, Ocampo-Martinez, Carlos, Torras, Carme, Rosasco, Lorenzo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.02811
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917982110744576
author Caldarelli, Edoardo
Chatalic, Antoine
Colomé, Adrià
Molinari, Cesare
Ocampo-Martinez, Carlos
Torras, Carme
Rosasco, Lorenzo
author_facet Caldarelli, Edoardo
Chatalic, Antoine
Colomé, Adrià
Molinari, Cesare
Ocampo-Martinez, Carlos
Torras, Carme
Rosasco, Lorenzo
contents In this paper, we study how the Koopman operator framework can be combined with kernel methods to effectively control nonlinear dynamical systems. While kernel methods have typically large computational requirements, we show how random subspaces (Nyström approximation) can be used to achieve huge computational savings while preserving accuracy. Our main technical contribution is deriving theoretical guarantees on the effect of the Nyström approximation. More precisely, we study the linear quadratic regulator problem, showing that the approximated Riccati operator converges at the rate $m^{-1/2}$, and the regulator objective, for the associated solution of the optimal control problem, converges at the rate $m^{-1}$, where $m$ is the random subspace size. Theoretical findings are complemented by numerical experiments corroborating our results.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02811
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Linear quadratic control of nonlinear systems with Koopman operator learning and the Nyström method
Caldarelli, Edoardo
Chatalic, Antoine
Colomé, Adrià
Molinari, Cesare
Ocampo-Martinez, Carlos
Torras, Carme
Rosasco, Lorenzo
Optimization and Control
Systems and Control
Machine Learning
In this paper, we study how the Koopman operator framework can be combined with kernel methods to effectively control nonlinear dynamical systems. While kernel methods have typically large computational requirements, we show how random subspaces (Nyström approximation) can be used to achieve huge computational savings while preserving accuracy. Our main technical contribution is deriving theoretical guarantees on the effect of the Nyström approximation. More precisely, we study the linear quadratic regulator problem, showing that the approximated Riccati operator converges at the rate $m^{-1/2}$, and the regulator objective, for the associated solution of the optimal control problem, converges at the rate $m^{-1}$, where $m$ is the random subspace size. Theoretical findings are complemented by numerical experiments corroborating our results.
title Linear quadratic control of nonlinear systems with Koopman operator learning and the Nyström method
topic Optimization and Control
Systems and Control
Machine Learning
url https://arxiv.org/abs/2403.02811