Lie-geometric trainability of quantum dynamical systems: avoiding barren plateaus via low-dimensional Lie subalgebras
Physica Scripta · 26.06.2026 · 101 (25) · 255107
DOI: 10.1088/1402-4896/ae7d6d ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 25.06.2026. Verfasst von Haijian Shao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben.
Abstract (Originalsprache)
We present a Lie-geometric framework for analyzing the trainability of quantum neural networks (QNNs) through the algebraic structure of their generator spaces. We prove that QNNs whose dynamics are restricted to polynomial-dimensional Lie subalgebras of su ( 2 n ) admit a polynomial lower bound on gradient variance, thereby avoiding barren plateaus by construction. In contrast, architectures exploring the full Lie algebra su ( 2 n ) exhibit exponentially vanishing gradient variance, O ( 2 − n ) , due to the exponential growth of the associated unitary orbit dimensions. Our results interpret barren plateaus as a geometric concentration phenomenon arising from high-dimensional Lie-group actions, rather than as an intrinsic limitation of parameterized quantum models. We further illustrate the mechanism using a finite-size collective-spin benchmark and a minimal two-qubit sanity check, both of which are consistent with the theoretical predictions.
Zitieren
APA
Shao, H., Wu, Y., Deng, X., & Jiang, Y. (2026). Lie-geometric trainability of quantum dynamical systems: avoiding barren plateaus via low-dimensional Lie subalgebras. Physica Scripta, 101(25), 255107. https://doi.org/10.1088/1402-4896/ae7d6d
Vancouver
Shao H, Wu Y, Deng X, Jiang Y. Lie-geometric trainability of quantum dynamical systems: avoiding barren plateaus via low-dimensional Lie subalgebras. Physica Scripta. 2026;101(25):255107. doi:10.1088/1402-4896/ae7d6d
BibTeX
@article{Shao2026,
author = {Shao, Haijian and Wu, Yujie and Deng, Xing and Jiang, Yingtao},
title = {Lie-geometric trainability of quantum dynamical systems: avoiding barren plateaus via low-dimensional Lie subalgebras},
journal = {Physica Scripta},
year = {2026},
volume = {101},
number = {25},
pages = {255107},
doi = {10.1088/1402-4896/ae7d6d}
}
EUVIMED