T空间解耦：用更少潜态实现扩散模型的更快分布式训练
Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states
AI总结：
该研究挑战扩散模型需大量潜态的假设，通过精心设计噪声调度实现少潜态训练，并提出T空间完全解耦的单潜态模型，组合后生成高质量样本且收敛速度快4-6倍。
摘要：
我们对扩散模型的一个基本假设提出挑战，即训练需要大量潜态或时间步长，以使逆向生成过程接近高斯分布。首先，我们证明通过精心选择噪声调度，在少量潜态（即$T\backsim32$）上训练的扩散模型，性能可与在大量潜态（$T\backsim1000$）上训练的模型相匹配。其次，我们将所需最小潜态数的极限推至单个潜态，称之为T空间的完全解耦。我们证明，通过组合多个独立训练的单潜态模型得到的解耦模型，可轻松生成高质量样本。我们通过大量实验表明，在两个不同数据集上，所提解耦模型在多种指标上的收敛速度快4-6倍。
英文摘要：
We challenge a fundamental assumption of diffusion models, namely, that a large number of latent-states or time-steps is required for training so that the reverse generative process is close to a Gaussian. We first show that with careful selection of a noise schedule, diffusion models trained over a small number of latent states (i.e. $T \sim 32$) match the performance of models trained over a much large number of latent states ($T \sim 1,000$). Second, we push this limit (on the minimum number of latent states required) to a single latent-state, which we refer to as complete disentanglement in T-space. We show that high quality samples can be easily generated by the disentangled model obtained by combining several independently trained single latent-state models. We provide extensive experiments to show that the proposed disentangled model provides 4-6$\times$ faster convergence measured across a variety of metrics on two different datasets.
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。
