DeepAI AI Chat
Log In Sign Up

Sample Complexity Lower Bounds for Linear System Identification

by   Yassir Jedra, et al.
KTH Royal Institute of Technology

This paper establishes problem-specific sample complexity lower bounds for linear system identification problems. The sample complexity is defined in the PAC framework: it corresponds to the time it takes to identify the system parameters with prescribed accuracy and confidence levels. By problem-specific, we mean that the lower bound explicitly depends on the system to be identified (which contrasts with minimax lower bounds), and hence really captures the identification hardness specific to the system. We consider both uncontrolled and controlled systems. For uncontrolled systems, the lower bounds are valid for any linear system, stable or not, and only depend of the system finite-time controllability gramian. A simplified lower bound depending on the spectrum of the system only is also derived. In view of recent finitetime analysis of classical estimation methods (e.g. ordinary least squares), our sample complexity lower bounds are tight for many systems. For controlled systems, our lower bounds are not as explicit as in the case of uncontrolled systems, but could well provide interesting insights into the design of control policy with minimal sample complexity.


page 1

page 2

page 3

page 4


Towards Testing Monotonicity of Distributions Over General Posets

In this work, we consider the sample complexity required for testing the...

Comments on the Du-Kakade-Wang-Yang Lower Bounds

Du, Kakade, Wang, and Yang recently established intriguing lower bounds ...

Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator

We provide a new finite-time analysis of the estimation error of stable ...

Linear Systems can be Hard to Learn

In this paper, we investigate when system identification is statisticall...

Optimal Learning of Mallows Block Model

The Mallows model, introduced in the seminal paper of Mallows 1957, is o...

Reproducibility in Learning

We introduce the notion of a reproducible algorithm in the context of le...

Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited

In this paper, we propose new problem-independent lower bounds on the sa...