发现扩散模型确定性采样会引发数据坍缩，导致生成结果过于集中。
On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models
- 提出新度量方法，量化了确定性采样中的数据坍缩现象。
- 实验证明在多种设置下均存在坍缩误差，且与噪声水平相关。
- 适合关注生成模型采样稳定性的研究人员参考。
尽管确定性采样器在扩散模型中被广泛采用，但其潜在局限性仍缺乏深入研究。本文首次识别出一种此前未被注意的现象——基于ODE的扩散采样中的坍缩误差，表现为生成数据在局部数据空间中过度集中。为量化该效应，我们引入一种新度量，并证实坍缩误差在多种设置下普遍存在。进一步分析发现存在‘跷跷板效应’：低噪声区域的梯度估计优化会损害高噪声区域的拟合效果。这种高噪声区的拟合偏差，结合确定性采样器的动力学特性，最终导致坍缩误差。基于上述洞察，我们通过采样、训练和架构改进等已有技术，提供了支持性实证证据。本工作为基于ODE的扩散采样中的坍缩误差提供了充分的实证依据，强调了分数学习与确定性采样之间相互作用的重要性，这一被忽视却基础性的问题亟需进一步研究。
原文摘要 · Abstract (English)
Despite the widespread adoption of deterministic samplers in diffusion models (DMs), their potential limitations remain largely unexplored. In this paper, we identify collapse errors, a previously unrecognized phenomenon in ODE-based diffusion sampling, where the sampled data is overly concentrated in local data space. To quantify this effect, we introduce a novel metric and demonstrate that collapse errors occur across a variety of settings. When investigating its underlying causes, we observe a see-saw effect, where score learning in low noise regimes adversely impacts the one in high noise regimes. This misfitting in high noise regimes, coupled with the dynamics of deterministic samplers, ultimately causes collapse errors. Guided by these insights, we apply existing techniques from sampling, training, and architecture to empirically support our explanation of collapse errors. This work provides intensive empirical evidence of collapse errors in ODE-based diffusion sampling, emphasizing the need for further research into the interplay between score learning and deterministic sampling, an overlooked yet fundamental aspect of diffusion models.
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。