arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.07992quant-phcs.AI
收藏

混合量子-经典决策模型Lipschitz常数的高效精确估计

Certified Lipschitz Bounds for Hybrid Quantum-Classical Decision Models

University of Tehran(德黑兰大学);Iran University of Science and Technology(伊朗科技大学)

Sajjad Hashemian, Mohammad Saeed Arvenaghi

AI总结:

本文提出一种结合经典神经网络与量子变分电路的统一凸优化框架,用于高效精确估计混合量子-经典模型的Lipschitz常数,从而支持公平性验证、鲁棒训练与泛化,并提升计算效率。

摘要:

本文提出了一种新颖的框架,用于高效且精确地估计混合量子-经典决策模型中的Lipschitz常数。我们的方法将经典神经网络与量子变分电路相结合,以解决学习理论中的关键问题,如公平性验证、鲁棒训练和泛化。通过统一的凸优化公式,我们扩展了现有的经典方法,以刻画经典层与量子层之间的相互作用。这种集成策略不仅提供了Lipschitz常数的紧致上界,而且相对于先前方法提高了计算效率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑