Spectral Filtering for Complex Linear Dynamical Systems
Quantum Physics
2026-05-11 v2 Artificial Intelligence
Abstract
We study the problem of learning complex-valued linear dynamical systems (CLDS) with sector-bounded spectrum. This class captures oscillatory and long-memory dynamics arising in signal processing, structured state space models, and quantum systems. We introduce a spectral filtering method based on the Slepian basis and show that learnability is governed by an effective dimension independent of the ambient state dimension. As a consequence, we obtain dimension-free regret bounds for sequence prediction in CLDS with spectrum contained in a sector of the unit disk.
Cite
@article{arxiv.2601.22400,
title = {Spectral Filtering for Complex Linear Dynamical Systems},
author = {Elad Hazan and Annie Marsden},
journal= {arXiv preprint arXiv:2601.22400},
year = {2026}
}