将光量子计算融入深度学习，提升能量模型采样与训练效率。
Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection
- 将相干伊辛机集成到PyTorch中，实现量子加速采样。
- 在单细胞和OpenWebText数据集上达到当前最优性能。
- 适合关注量子-经典混合架构的科研人员。
本文提出Kaiwu-PyTorch-Plugin（KPP），实现深度学习与光子量子计算的多维融合。KPP将相干伊辛机（Coherent Ising Machine）引入PyTorch生态，解决能量模型中的经典计算低效问题。该框架在三个关键方面推动量子集成：加速玻尔兹曼采样、通过主动采样优化训练数据，以及构建如QBM-VAE和Q-Diffusion等混合架构。在单细胞和OpenWebText数据集上的实验表明，KPP可实现领先性能，验证了完整的量子-经典协同范式。
原文摘要 · Abstract (English)
This paper introduces the Kaiwu-PyTorch-Plugin (KPP) to bridge Deep Learning and Photonic Quantum Computing across multiple dimensions. KPP integrates the Coherent Ising Machine into the PyTorch ecosystem, addressing classical inefficiencies in Energy-Based Models. The framework facilitates quantum integration in three key aspects: accelerating Boltzmann sampling, optimizing training data via Active Sampling, and constructing hybrid architectures like QBM-VAE and Q-Diffusion. Empirical results on single-cell and OpenWebText datasets demonstrate KPPs ability to achieve SOTA performance, validating a comprehensive quantum-classical paradigm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。