Learning Networked Linear Dynamical Systems under Non-white Excitation from a Single Trajectory

10/02/2021
by   Harish Doddi, et al.
0

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 driven by unobserved not-white wide-sense stationary (WSS) inputs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/31/2023

Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs

In this article, the optimal sample complexity of learning the underlyin...
research
10/08/2020

Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples

In this work, we study the problem of learning partially observed linear...
research
09/16/2016

Gradient Descent Learns Linear Dynamical Systems

We prove that gradient descent efficiently converges to the global optim...
research
02/04/2020

Proper Learning of Linear Dynamical Systems as a Non-Commutative Polynomial Optimisation Problem

There has been much recent progress in forecasting the next observation ...
research
09/26/2020

Estimating Linear Dynamical Networks of Cyclostationary Processes

Topology learning is an important problem in dynamical systems with impl...
research
03/27/2023

Learning linear dynamical systems under convex constraints

We consider the problem of identification of linear dynamical systems fr...
research
05/17/2023

Exact Recovery for System Identification with More Corrupt Data than Clean Data

In this paper, we study the system identification problem for linear dis...

Please sign up or login with your details

Forgot password? Click here to reset