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 2607.07072cs.LG
收藏

一种用于图像生成的混合量子-经典扩散模型

An Hybrid Quantum-Classical Diffusion Model for Image Generation

Qipeng Qian, Keli Deng, Yuntao Qian

AI总结:

研究针对量子扩散模型应用于经典高维数据的限制,提出结合经典自动编码器与混合态量子去噪扩散概率模型的混合生成管道,用于图像生成,通过简化反向动力学算法展示该方法在MNIST图像生成上的效果及意义。

摘要:

量子扩散模型通过直接对量子态进行加噪和去噪,为生成学习提供了一条符合物理规律的途径。然而,将此类模型应用于经典高维数据时,受到状态编码的量子比特成本和模拟大型密度算子的计算负担的限制。我们提出了一种可扩展的混合生成管道,它将用于降维的经典自动编码器与在学习的潜在空间中运行的混合态量子去噪扩散概率模型(MSQuDDPM)相结合。自动编码器将数据压缩成紧凑的潜在码,可嵌入到小量子比特希尔伯特空间,然后量子扩散模型学习潜在密度算子上的生成分布,并将样本解码回原始域。在算法上,我们通过预测时间步\(t\)时的干净状态\(\rho_0\)的估计值,并通过解析反向传播规则计算一步反向更新,简化了反向动力学,而不是为\(\rho_{t - 1}\)学习一个显式预测器。我们在MNIST图像生成上展示了所提出的方法,并讨论了在实际量子比特预算下,混合态量子扩散如何作为混合量子-经典生成建模的实用主干。

英文摘要:

Quantum diffusion models provide a physics-consistent route to generative learning by formulating noising and denoising directly on quantum states. However, applying such models to classical high-dimensional data is constrained by the qubit cost of state encoding and the computational burden of simulating large density operators. We propose a scalable hybrid generative pipeline that combines a classical autoencoder for dimensionality reduction with a mixed-state quantum denoising diffusion probabilistic model (MSQuDDPM) operating in the learned latent space. The autoencoder compresses data into compact latent codes that can be embedded into a small-qubit Hilbert space, after which the quantum diffusion model learns a generative distribution over latent density operators and decodes samples back to the original domain. Algorithmically, we simplify the reverse dynamics by predicting an estimate of the clean state $ρ_0$ at timestep $t$ and computing the one-step reverse update via an analytic backward propagation rule, rather than learning an explicit predictor for $ρ_{t-1}$. We demonstrate the proposed approach on MNIST image generation and discuss how mixed-state quantum diffusion can serve as a practical backbone for hybrid quantum--classical generative modeling under realistic qubit budgets.

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。

↑