In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates extended training periods and may potentially impede modeling flexibility and capacity. To counteract these challenges, we propose leveraging the independence of learning tasks at different time points inherent to DPMs. More specifically, we partition the learning task by utilizing independent networks, each dedicated to learning the evolution of scores within a specific time sub-interval. Further, inspired by residual flows, we extend this strategy to its logical conclusion by employing separate networks to independently model the score at each individual time point. As empirically demonstrated on synthetic and image datasets, our approach not only significantly accelerates the training process by introducing an additional layer of parallelization atop data parallelization, but it also enhances density estimation performance when compared to the conventional training methodology for DPMs.

翻译：在扩散概率模型（DPMs）中，通过单一时间相关神经网络建模得分演化过程，不仅需要较长的训练周期，还可能制约模型的灵活性与容量。为应对这些挑战，我们提出利用DPMs在不同时间点上的学习任务独立性。具体而言，我们采用独立网络对学习任务进行划分，每个网络专门学习特定时间子区间内的得分演化。进一步受残差流启发，我们将这一策略推向极致——为每个单独时间点的得分建模均使用独立网络。在合成数据集与图像数据集上的实验表明，与DPMs的传统训练方法相比，我们的方法通过在数据并行化基础上引入额外并行化层，不仅显著加速了训练过程，还提升了密度估计性能。