Efficient Learning of a Linear Dynamical System with Stability Guarantees

02/06/2021
by   Wouter Jongeneel, et al.
0

We propose a principled method for projecting an arbitrary square matrix to the non-convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we show that this projection is optimal in an information-theoretic sense and that it simply amounts to shifting the initial matrix by an optimal linear quadratic feedback gain, which can be computed exactly and highly efficiently by solving a standard linear quadratic regulator problem. The proposed approach allows us to learn the system matrix of a stable linear dynamical system from a single trajectory of correlated state observations. The resulting estimator is guaranteed to be stable and offers explicit statistical bounds on the estimation error.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2021

Subspace Method for the Estimation of Large-Scale Structured Real Stability Radius

We consider the autonomous dynamical system x' = Ax, with A ∈ℝ^n× n. Thi...
research
01/23/2023

A New Approach to Learning Linear Dynamical Systems

Linear dynamical systems are the foundational statistical model upon whi...
research
06/11/2021

Safety of Dynamical Systems with Multiple Non-Convex Unsafe Sets Using Control Barrier Functions

This paper presents an approach to deal with safety of dynamical systems...
research
01/24/2023

Inference of Continuous Linear Systems from Data with Guaranteed Stability

Machine-learning technologies for learning dynamical systems from data p...
research
02/16/2022

Single Trajectory Nonparametric Learning of Nonlinear Dynamics

Given a single trajectory of a dynamical system, we analyze the performa...
research
06/06/2020

Learning Memory-Efficient Stable Linear Dynamical Systems for Prediction and Control

Learning a stable Linear Dynamical System (LDS) from data involves creat...
research
11/25/2021

Model Reduction of Linear Dynamical Systems via Balancing for Bayesian Inference

We consider the Bayesian approach to the linear Gaussian inference probl...

Please sign up or login with your details

Forgot password? Click here to reset