arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.22964quant-phcond-mat.quant-gascs.LGstat.ML
收藏

基于量子模型的泛化分析的PAC-Bayesian方法

A PAC-Bayesian approach to generalization for quantum models

Department of Physical Chemistry, University of the Basque Country UPV/EHU(巴斯克大学化学系);EHU Quantum Center, University of the Basque Country UPV/EHU(巴斯克大学量子中心);TECNALIA, Basque Research and Technology Alliance (BRTA)(TECNALIA巴斯克研究与技术联盟);Department of Computer Science, University of Warwick, UK(沃里克大学计算机科学系);Dahlem Center for Complex Quantum Systems, Freie Universität Berlin(柏林自由大学复杂量子系统中心);Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫海因里希·赫兹研究所)

Pablo Rodriguez-Grasa, Matthias C. Caro, Jens Eisert, Elies Gil-Fuster, Franz J. Schreiber, Carlos Bravo-Prieto

AI总结:

本文提出首个量子模型的PAC-Bayesian泛化界,通过分析分层电路中的通用量子通道,建立依赖于学习参数矩阵范数的非均匀界,并通过数值实验验证理论框架。

摘要:

泛化是机器学习理论中的核心概念,但针对量子模型,通常通过依赖模型整体容量的统一界进行分析,这些界往往过于宽松且对实际训练和学习过程不敏感。本文通过分析由通用量子通道组成的分层电路,推导出首个广泛量子模型的PAC-Bayesian泛化界,包括耗散操作如中间电路测量和前馈。通过通道扰动分析,建立依赖于学习参数矩阵范数的非均匀界,并将结果扩展到对称约束的等价量子模型,通过数值实验验证了理论框架。本文为量子机器学习中的泛化理解提供了可操作的模型设计见解,并建立了更细致理解泛化的基础工具。

英文摘要:

Generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function learned. These capacity-based uniform bounds are often too loose and entirely insensitive to the actual training and learning process. Previous theoretical guarantees have failed to provide non-uniform, data-dependent bounds that reflect the specific properties of the learned solution rather than the worst-case behavior of the entire hypothesis class. To address this limitation, we derive the first PAC-Bayesian generalization bounds for a broad class of quantum models by analyzing layered circuits composed of general quantum channels, which include dissipative operations such as mid-circuit measurements and feedforward. Through a channel perturbation analysis, we establish non-uniform bounds that depend on the norms of learned parameter matrices; we extend these results to symmetry-constrained equivariant quantum models; and we validate our theoretical framework with numerical experiments. This work provides actionable model design insights and establishes a foundational tool for a more nuanced understanding of generalization in quantum machine learning.

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。

↑