Log In Sign Up

Active Learning for Identification of Linear Dynamical Systems

by   Andrew Wagenmaker, et al.

We propose an algorithm to actively estimate the parameters of a linear dynamical system. Given complete control over the system's input, our algorithm adaptively chooses the inputs to accelerate estimation. We show a finite time bound quantifying the estimation rate our algorithm attains and prove matching upper and lower bounds which guarantee its asymptotic optimality, up to constants. In addition, we show that this optimal rate is unattainable when using Gaussian noise to excite the system, even with optimally tuned covariance, and analyze several examples where our algorithm provably improves over rates obtained by playing noise. Our analysis critically relies on a novel result quantifying the error in estimating the parameters of a dynamical system when arbitrary periodic inputs are being played. We conclude with numerical examples that illustrate the effectiveness of our algorithm in practice.


page 1

page 2

page 3

page 4


Active Learning for Nonlinear System Identification with Guarantees

While the identification of nonlinear dynamical systems is a fundamental...

Learning Linear Dynamical Systems with Semi-Parametric Least Squares

We analyze a simple prefiltered variation of the least squares estimator...

Task-Optimal Exploration in Linear Dynamical Systems

Exploration in unknown environments is a fundamental problem in reinforc...

Dynamic Structure Estimation from Bandit Feedback

This work present novel method for structure estimation of an underlying...

Improved rates for identification of partially observed linear dynamical systems

Identification of a linear time-invariant dynamical system from partial ...

A New Framework for H_2-Optimal Model Reduction

In this contribution, a new framework for H2-optimal reduction of multip...