Generalization analysis of quantum neural networks using dynamical Lie algebras
Quantum Physics
2025-04-15 v1
Abstract
The paper presents a generalization bound for quantum neural networks based on a dynamical Lie algebra. Using covering numbers derived from a dynamical Lie algebra, the Rademacher complexity is derived to calculate the generalization bound. The obtained result indicates that the generalization bound is scaled by O(sqrt(dim(g))), where g denotes a dynamical Lie algebra of generators. Additionally, the upper bound of the number of the trainable parameters in a quantum neural network is presented. Numerical simulations are conducted to confirm the validity of the obtained results.
Keywords
Cite
@article{arxiv.2504.09771,
title = {Generalization analysis of quantum neural networks using dynamical Lie algebras},
author = {Hiroshi Ohno},
journal= {arXiv preprint arXiv:2504.09771},
year = {2025}
}