解耦总方差和信噪比改进扩散模型
Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models
AI总结:
提出总方差/信噪比解耦(TV/SNR)框架,通过独立控制TV和SNR改进扩散模型,发现恒定TV调度和推广最优传输流匹配的SNR调度能显著提升生成性能。
摘要:
扩散模型较长的采样时间仍然是一个重要的瓶颈,这可以通过减少扩散时间步数来缓解。然而,较少步数下样本的质量高度依赖于噪声调度,即在每一步中引入噪声和降低信号的具体方式。尽管先前的工作在原始的保方差和爆方差调度上有所改进,但这些方法被动地调整总方差,而无法对其进行直接控制。在本研究中,我们提出了一种新颖的总方差/信噪比解耦(TV/SNR)框架,其中TV和SNR可以独立控制。我们的方法表明,TV呈指数级爆炸的调度通常可以通过采用恒定的TV调度同时保持相同的SNR调度来改进。此外,将最优传输流匹配的SNR调度进行推广,显著提升了生成性能。我们的发现在各种反向扩散求解器和包括分子结构和图像生成在内的多样化应用中均成立。
英文摘要:
Diffusion models have been widely adopted as a powerful generative framework across numerous scientific domains, yet their inherently iterative sampling process remains a significant computational bottleneck. While this is typically mitigated by reducing the number of reverse diffusion steps, sample quality becomes highly sensitive to the chosen noise schedule, i.e. the manner in which noise is introduced and the signal is reduced at each step. Although prior work has improved on the original variance-preserving and variance-exploding schedules, these approaches passively adjust the total variance, without direct independent control over it. In this work, we propose a novel total-variance/signal-to-noise-ratio disentangled (TV/SNR) framework, where TV and SNR can be controlled independently. Our approach reveals that schedules with exponentially exploding TV can be consistently improved by adopting a constant TV schedule while preserving the underlying SNR schedule. Furthermore, we demonstrate that generalizing the SNR schedule of optimal transport flow matching significantly enhances generation efficiency. Crucially, these gains remain consistent across various reverse diffusion solvers and reduce the search space to two independent and interpretable parameters, enabling fast and robust sampling for complex scientific applications, such as molecular structure generation.
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。