Generalization analysis of quantum neural networks using dynamical Lie algebras

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.