Efficient Learning of Distributed Linear-Quadratic Controllers

by   Salar Fattahi, et al.

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed controllers can be learned with sub-linear sample complexity and computed with near-linear time complexity, both measured with respect to the dimension of the system. In particular, we provide sharp end-to-end guarantees on the stability and the performance of the designed distributed controller and prove that for sparse systems, the number of samples needed to guarantee robust and near optimal performance of the designed controller can be significantly smaller than the dimension of the system. Finally, we show that the proposed optimization problem can be solved to global optimality with near-linear time complexity by iteratively solving a series of small quadratic programs.


page 1

page 2

page 3

page 4


Near-Optimal Distributed Linear-Quadratic Regulator for Networked Systems

This paper studies the trade-off between the degree of decentralization ...

Distributed Model Predictive Control for Linear Systems with Adaptive Terminal Sets

In this paper, we propose a distributed model predictive control (DMPC) ...

Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms

We study the problem of robustly learning multi-dimensional histograms. ...

The PCP-like Theorem for Sub-linear Time Inapproximability

In this paper we propose the PCP-like theorem for sub-linear time inappr...

Learning Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

We present the first approach for learning – from a single trajectory – ...

Safely Learning to Control the Constrained Linear Quadratic Regulator

We study the constrained linear quadratic regulator with unknown dynamic...

A new compressed cover tree guarantees a near linear parameterized complexity for all k-nearest neighbors search in metric spaces

This paper studies the classical problem of finding all k nearest neighb...