优化采样步数分配，提升离散扩散模型生成速度与质量
$\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models
- 通过最小化复合解码误差，智能调整采样步数分配
- 在图像、音乐、文本生成任务中显著提升样本质量
- 无需额外计算开销，适合追求高效生成的场景
扩散模型在连续空间中取得显著成功，推动了离散变量的离散扩散模型（DDMs）发展。尽管近期进展不断，DDMs仍面临采样速度慢的问题。虽然并行采样方法如τ-跳跃可加速过程，但会引入复合解码误差（CDE），导致真实分布与并行生成近似之间出现偏差，降低样本质量。本文提出新方法Jump Your Steps（JYS），通过最小化CDE优化离散采样步数分配，无需额外计算成本。我们推导出CDE的实际上限，并设计高效算法搜索最优采样调度。在图像、音乐和文本生成任务上的广泛实验表明，JYS显著提升采样质量，成为提升快速采样下DDM性能的通用框架。
原文摘要 · Abstract (English)
Diffusion models have seen notable success in continuous domains, leading to the development of discrete diffusion models (DDMs) for discrete variables. Despite recent advances, DDMs face the challenge of slow sampling speeds. While parallel sampling methods like $τ$-leaping accelerate this process, they introduce $\textit{Compounding Decoding Error}$ (CDE), where discrepancies arise between the true distribution and the approximation from parallel token generation, leading to degraded sample quality. In this work, we present $\textit{Jump Your Steps}$ (JYS), a novel approach that optimizes the allocation of discrete sampling timesteps by minimizing CDE without extra computational cost. More precisely, we derive a practical upper bound on CDE and propose an efficient algorithm for searching for the optimal sampling schedule. Extensive experiments across image, music, and text generation show that JYS significantly improves sampling quality, establishing it as a versatile framework for enhancing DDM performance for fast sampling.
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。