Variance-Reduction Guidance: Sampling Trajectory Optimization for Diffusion Models
This addresses a key bottleneck in diffusion model sampling for generative tasks, offering a practical, model-agnostic solution that is incremental but broadly applicable.
The paper tackles the accumulation of prediction errors in diffusion models during sampling, which degrades generation quality, and introduces Variance-Reduction Guidance (VRG) to optimize sampling trajectories without model changes, resulting in significant quality improvements across various datasets.
Diffusion models have become emerging generative models. Their sampling process involves multiple steps, and in each step the models predict the noise from a noisy sample. When the models make prediction, the output deviates from the ground truth, and we call such a deviation as \textit{prediction error}. The prediction error accumulates over the sampling process and deteriorates generation quality. This paper introduces a novel technique for statistically measuring the prediction error and proposes the Variance-Reduction Guidance (VRG) method to mitigate this error. VRG does not require model fine-tuning or modification. Given a predefined sampling trajectory, it searches for a new trajectory which has the same number of sampling steps but produces higher quality results. VRG is applicable to both conditional and unconditional generation. Experiments on various datasets and baselines demonstrate that VRG can significantly improve the generation quality of diffusion models. Source code is available at https://github.com/shifengxu/VRG.