通过临界阻尼优化扩散模型动态，提升采样速度与质量。
Critically Damped Third-Order Langevin Dynamics
- 对三阶朗之万动力学进行临界阻尼改造，加速收敛。
- 在瑞士卷和CIFAR-10上验证，FID指标显著降低。
- 适合关注扩散模型加速与稳定性的研究者。
尽管系统分析在控制理论中已有数十年研究，但仅近来才被用于改进去噪扩散概率模型的收敛性。本文提出对最新扩散方法三阶朗之万动力学（TOLD）的改进，命名为TOLD++。该方法通过分析前向转移矩阵的特征值，实现类似Dockhorn提出的临界阻尼朗之万动力学（CLD）的临界阻尼设计。理论上，TOLD++收敛速度优于TOLD。实验验证显示，在瑞士卷数据集和CIFAR-10上，TOLD++的采样效率更高，FID指标下降显著。
原文摘要 · Abstract (English)
While systems analysis has been studied for decades in the context of control theory, it has only been recently used to improve the convergence of Denoising Diffusion Probabilistic Models. This work describes a novel improvement to Third- Order Langevin Dynamics (TOLD), a recent diffusion method that performs better than its predecessors. This improvement, abbreviated TOLD++, is carried out by critically damping the TOLD forward transition matrix similarly to Dockhorn's Critically-Damped Langevin Dynamics (CLD). Specifically, it exploits eigen-analysis of the forward transition matrix to derive the optimal set of dynamics under the original TOLD scheme. TOLD++ is theoretically guaranteed to converge faster than TOLD, and its faster convergence is verified on the Swiss Roll toy dataset and CIFAR-10 dataset according to the FID metric.
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。