A New Approach to Controlling Linear Dynamical Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brahmbhatt, Anand, Buzaglo, Gon, Druchyna, Sofiia, Hazan, Elad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916675139403776
author Brahmbhatt, Anand
Buzaglo, Gon
Druchyna, Sofiia
Hazan, Elad
author_facet Brahmbhatt, Anand
Buzaglo, Gon
Druchyna, Sofiia
Hazan, Elad
contents We propose a new method for controlling linear dynamical systems under adversarial disturbances and cost functions. Our algorithm achieves a running time that scales polylogarithmically with the inverse of the stability margin, improving upon prior methods with polynomial dependence maintaining the same regret guarantees. The technique, which may be of independent interest, is based on a novel convex relaxation that approximates linear control policies using spectral filters constructed from the eigenvectors of a specific Hankel matrix.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03952
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A New Approach to Controlling Linear Dynamical Systems
Brahmbhatt, Anand
Buzaglo, Gon
Druchyna, Sofiia
Hazan, Elad
Systems and Control
Machine Learning
Optimization and Control
We propose a new method for controlling linear dynamical systems under adversarial disturbances and cost functions. Our algorithm achieves a running time that scales polylogarithmically with the inverse of the stability margin, improving upon prior methods with polynomial dependence maintaining the same regret guarantees. The technique, which may be of independent interest, is based on a novel convex relaxation that approximates linear control policies using spectral filters constructed from the eigenvectors of a specific Hankel matrix.
title A New Approach to Controlling Linear Dynamical Systems
topic Systems and Control
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2504.03952