OCLGMLSep 21, 2019

Efficient Learning of Distributed Linear-Quadratic Controllers

arXiv:1909.09895v26 citations
Originality Highly original
AI Analysis

This addresses efficient control design for large-scale sparse systems, offering significant sample and computational savings.

The paper tackles the problem of designing distributed controllers for unknown sparse linear systems, achieving near-optimal performance with sub-linear sample complexity and near-linear time complexity relative to system dimension.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes