用高效估计器提升离散扩散模型生成质量，适用于二值与量子数据。
Discrete Diffusion with Sample-Efficient Estimators for Conditionals
- 以单点条件概率为核心，结合轮转噪声与去噪机制建模
- 在MNIST等数据上优于主流方法，各项指标均有提升
- 适合需要高精度生成的科学模拟与量子系统建模场景
我们研究一种离散去噪扩散框架，通过样本高效的单点条件概率估计器（NeurISE）与轮转噪声-去噪动态，实现离散状态空间上的生成建模。不近似离散得分函数，而是直接以单点条件概率作为反向扩散过程的核心参数。在合成伊辛模型、MNIST及由D-Wave量子退火器生成的科学数据集（包括合成庞茨模型与一维量子系统）上进行受控实验，结果表明该方法在二值数据集上优于主流比率方法，在总变差、交叉相关性和核密度估计等指标上均取得更优表现。
原文摘要 · Abstract (English)
We study a discrete denoising diffusion framework that integrates a sample-efficient estimator of single-site conditionals with round-robin noising and denoising dynamics for generative modeling over discrete state spaces. Rather than approximating a discrete analog of a score function, our formulation treats single-site conditional probabilities as the fundamental objects that parameterize the reverse diffusion process. We employ a sample-efficient method known as Neural Interaction Screening Estimator (NeurISE) to estimate these conditionals in the diffusion dynamics. Controlled experiments on synthetic Ising models, MNIST, and scientific data sets produced by a D-Wave quantum annealer, synthetic Potts model and one dimensional quantum systems demonstrate the proposed approach. On the binary data sets, these experiments demonstrate that the proposed approach outperforms popular existing methods including ratio-based approaches, achieving improved performance in total variation, cross-correlations, and kernel density estimation metrics.
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。