arXiv:2503.07992 · v2
Certified Lipschitz Bounds for Hybrid Quantum-Classical Decision Models
摘要
We study certified upper bounds on Lipschitz constants for hybrid quantum-classical decision models, which combine classical neural-network layers with parameterized quantum circuits. We pair an SDP-based certificate for classical layers with an exact spectral characterization for probability-output quantum models. For hybrid architectures, these componentwise estimates are connected through the encoding maps to obtain a certified composition bound for the complete model. The resulting bounds support sensitivity analyses relevant to robustness, stability, generalization, and fairness.
作者备注：14 pages, 6 figuers, a previous version of this article is published in the 2025 Iranian International Artificial Intelligence Conference (ICAI)