Distributed Koopman Operator Learning from Sequential Observations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Azarbahram, Ali, Liu, Shenyu, Incremona, Gian Paolo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911602260836352
author Azarbahram, Ali
Liu, Shenyu
Incremona, Gian Paolo
author_facet Azarbahram, Ali
Liu, Shenyu
Incremona, Gian Paolo
contents This paper presents a distributed Koopman operator learning framework for modeling unknown nonlinear dynamics using sequential observations from multiple agents. Each agent estimates a local Koopman approximation based on lifted data and collaborates over a communication graph to reach exponential consensus on a consistent distributed approximation. The approach supports distributed computation under asynchronous and resource-constrained sensing. Its performance is demonstrated through simulation results, validating convergence and predictive accuracy under sensing-constrained scenarios and limited communication.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20071
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distributed Koopman Operator Learning from Sequential Observations
Azarbahram, Ali
Liu, Shenyu
Incremona, Gian Paolo
Systems and Control
This paper presents a distributed Koopman operator learning framework for modeling unknown nonlinear dynamics using sequential observations from multiple agents. Each agent estimates a local Koopman approximation based on lifted data and collaborates over a communication graph to reach exponential consensus on a consistent distributed approximation. The approach supports distributed computation under asynchronous and resource-constrained sensing. Its performance is demonstrated through simulation results, validating convergence and predictive accuracy under sensing-constrained scenarios and limited communication.
title Distributed Koopman Operator Learning from Sequential Observations
topic Systems and Control
url https://arxiv.org/abs/2509.20071