paper-with-me

Papers

Efficient and passive learning of networked dynamical systems driven by non-white exogenous inputs

2021-10-02 · Harish Doddi, Deepjyoti Deka, Saurav Talukdar, Murti Salapaka

We consider a networked linear dynamical system with $p$ agents/nodes. We study the problem of learning the underlying graph of interactions/dependencies from observations of the nodal trajectories over a time-interval $T$. We present a regularized non-casual consistent estimator for this problem and analyze its sample complexity over two regimes: (a) where the interval $T$ consists of $n$ i.i.d. observation windows of length $T/n$ (restart and record), and (b) where $T$ is one continuous observation window (consecutive). Using the theory of $M$-estimators, we show that the estimator recovers the underlying interactions, in either regime, in a time-interval that is logarithmic in the system size $p$. To the best of our knowledge, this is the first work to analyze the sample complexity of learning linear dynamical systems \emph{driven by unobserved not-white wide-sense stationary (WSS) inputs}.

📄 PDF Abstract BibTeX arXiv:2110.00852

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Heterogeneous 6G Networked Sensing Architecture with Active and Passive Anchors

2023-05-04 · QiPeng Wang, Liang Liu, Shuowen Zhang, Boya Di 외

In the future 6G integrated sensing and communication (ISAC) cellular systems, networked sensing is a promising technique that can leverage the cooperation among the base stations (BSs) to perform high-resolution localiz…

Integrated sensing and communicationISAC

Tunable Passivity Control for Centralized Multiport Networked Systems

2025-11-07 · Xingyuan Zhou, Peter Paik, S. Farokh Atashzar arxiv

Centralized Multiport Networked Dynamic (CMND) systems have emerged as a key architecture with applications in several complex network systems, such as multilateral telerobotics and multi-agent control. These systems con…

Learning Networked Dynamical System Models with Weak Form and Graph Neural Networks

2024-07-23 · Yin Yu, Daning Huang, Seho Park, Herschel C. Pangborn

This paper presents a sequence of two approaches for the data-driven control-oriented modeling of networked systems, i.e., the systems that involve many interacting dynamical components. First, a novel deep learning appr…

Form

Structural Inference of Networked Dynamical Systems with Universal Differential Equations

2022-07-11 · James Koch, Zhao Chen, Aaron Tuor, Jan Drgona 외

Networked dynamical systems are common throughout science in engineering; e.g., biological networks, reaction networks, power systems, and the like. For many such systems, nonlinearity drives populations of identical (or…

Compositional Neural Certificates for Networked Dynamical Systems

2023-03-25 · Songyuan Zhang, Yumeng Xiu, Guannan Qu, Chuchu Fan

Developing stable controllers for large-scale networked dynamical systems is crucial but has long been challenging due to two key obstacles: certifiability and scalability. In this paper, we present a general framework t…