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.
View on arXiv@article{brahmbhatt2025_2504.03952,
title={ A New Approach to Controlling Linear Dynamical Systems },
author={ Anand Brahmbhatt and Gon Buzaglo and Sofiia Druchyna and Elad Hazan },
journal={arXiv preprint arXiv:2504.03952},
year={ 2025 }
}