Comprehensive Analysis of Diffusion-Based Generative Models: Optimizing Training and Sampling for Effective Generation
This paper provides a full error analysis of diffusion-based generative models by combining the optimization of the training process and the analysis of the sampling process. It establishes exponential convergence of gradient descent training for denoising score matching and extends the sampling error analysis to the variance exploding setting, leading to a comprehensive understanding of the design space of diffusion models.
Enhancing Generative Models with Approximated Optimal Transport
The author introduces the Approximated Optimal Transport (AOT) technique to improve diffusion-based generative models by integrating optimal transport into the training process, resulting in superior image quality and reduced sampling steps. The core thesis is that AOT enhances the performance of diffusion models by reducing curvature in ODE trajectories.